Authors: Ruggero Marino Lazzaroni, Alessandro Angioi, Michelangelo Puliga, Davide Sanna, Roberto Marras
Abstract: Large language models (LLMs) show increasing potential in education, yet benchmarks for non-English languages in specialized domains remain scarce. We introduce MedBench-IT, the first comprehensive benchmark for evaluating LLMs on Italian medical university entrance examinations. Sourced from Edizioni Simone, a leading preparatory materials publisher, MedBench-IT comprises 17,410 expert-written multiple-choice questions across six subjects (Biology, Chemistry, Logic, General Culture, Mathematics, Physics) and three difficulty levels. We evaluated diverse models including proprietary LLMs (GPT-4o, Claude series) and resource-efficient open-source alternatives (<30B parameters) focusing on practical deployability. Beyond accuracy, we conducted rigorous reproducibility tests (88.86% response consistency, varying by subject), ordering bias analysis (minimal impact), and reasoning prompt evaluation. We also examined correlations between question readability and model performance, finding a statistically significant but small inverse relationship. MedBench-IT provides a crucial resource for Italian NLP community, EdTech developers, and practitioners, offering insights into current capabilities and standardized evaluation methodology for this critical domain.
Authors: William Chen, Chutong Meng, Jiatong Shi, Martijn Bartelds, Shih-Heng Wang, Hsiu-Hsuan Wang, Rafael Mosquera, Sara Hincapie, Dan Jurafsky, Antonis Anastasopoulos, Hung-yi Lee, Karen Livescu, Shinji Watanabe
Abstract: Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Interspeech 2025 ML-SUPERB 2.0 Challenge. We construct a new test suite that consists of data from 200+ languages, accents, and dialects to evaluate SOTA multilingual speech models. The challenge also introduces an online evaluation server based on DynaBench, allowing for flexibility in model design and architecture for participants. The challenge received 5 submissions from 3 teams, all of which outperformed our baselines. The best-performing submission achieved an absolute improvement in LID accuracy of 23% and a reduction in CER of 18% when compared to the best baseline on a general multilingual test set. On accented and dialectal data, the best submission obtained 30.2% lower CER and 15.7% higher LID accuracy, showing the importance of community challenges in making speech technologies more inclusive.
Authors: Zhiyin Tan, Jennifer D'Souza
Abstract: This study presents a framework for automated evaluation of dynamically evolving topic models using Large Language Models (LLMs). Topic modeling is essential for organizing and retrieving scholarly content in digital library systems, helping users navigate complex and evolving knowledge domains. However, widely used automated metrics, such as coherence and diversity, often capture only narrow statistical patterns and fail to explain semantic failures in practice. We introduce a purpose-oriented evaluation framework that employs nine LLM-based metrics spanning four key dimensions of topic quality: lexical validity, intra-topic semantic soundness, inter-topic structural soundness, and document-topic alignment soundness. The framework is validated through adversarial and sampling-based protocols, and is applied across datasets spanning news articles, scholarly publications, and social media posts, as well as multiple topic modeling methods and open-source LLMs. Our analysis shows that LLM-based metrics provide interpretable, robust, and task-relevant assessments, uncovering critical weaknesses in topic models such as redundancy and semantic drift, which are often missed by traditional metrics. These results support the development of scalable, fine-grained evaluation tools for maintaining topic relevance in dynamic datasets. All code and data supporting this work are accessible at https://github.com/zhiyintan/topic-model-LLMjudgment.
Authors: Amal Chebbi, Babajide Kolade
Abstract: Large Language Models have demonstrated impressive capabilities across various domains. However, their general-purpose nature often limits their effectiveness in specialized fields such as energy, where deep technical expertise and precise domain knowledge are essential. In this paper, we introduce EnergyGPT, a domain-specialized language model tailored for the energy sector, developed by fine-tuning LLaMA 3.1-8B model using Supervised Fine-Tuning on a high-quality, curated corpus of energy-related texts. We present a complete development pipeline, including data collection and curation, model fine-tuning, benchmark design and LLM-judge choice, evaluation and deployment. Through this work, we demonstrate that our training strategy enables improvements in domain relevance and performance without the need for large-scale infrastructure. By evaluating the performance of the model using domain-specific question-answering benchmarks, our results demonstrate that EnergyGPT outperforms the base model in most of the energy-related language understanding and generation tasks.
Authors: Zonghai Yao, Michael Sun, Won Seok Jang, Sunjae Kwon, Soie Kwon, Hong Yu
Abstract: Discharge communication is a critical yet underexplored component of patient care, where the goal shifts from diagnosis to education. While recent large language model (LLM) benchmarks emphasize in-visit diagnostic reasoning, they fail to evaluate models' ability to support patients after the visit. We introduce DischargeSim, a novel benchmark that evaluates LLMs on their ability to act as personalized discharge educators. DischargeSim simulates post-visit, multi-turn conversations between LLM-driven DoctorAgents and PatientAgents with diverse psychosocial profiles (e.g., health literacy, education, emotion). Interactions are structured across six clinically grounded discharge topics and assessed along three axes: (1) dialogue quality via automatic and LLM-as-judge evaluation, (2) personalized document generation including free-text summaries and structured AHRQ checklists, and (3) patient comprehension through a downstream multiple-choice exam. Experiments across 18 LLMs reveal significant gaps in discharge education capability, with performance varying widely across patient profiles. Notably, model size does not always yield better education outcomes, highlighting trade-offs in strategy use and content prioritization. DischargeSim offers a first step toward benchmarking LLMs in post-visit clinical education and promoting equitable, personalized patient support.
Authors: Zahra Atf, Peter R Lewis
Abstract: Large language models (LLMs) are increasingly used in high-stakes settings, where explaining uncertainty is both technical and ethical. Probabilistic methods are often opaque and misaligned with expectations of transparency. We propose a framework based on rule-based moral principles for handling uncertainty in LLM-generated text. Using insights from moral psychology and virtue ethics, we define rules such as precaution, deference, and responsibility to guide responses under epistemic or aleatoric uncertainty. These rules are encoded in a lightweight Prolog engine, where uncertainty levels (low, medium, high) trigger aligned system actions with plain-language rationales. Scenario-based simulations benchmark rule coverage, fairness, and trust calibration. Use cases in clinical and legal domains illustrate how moral reasoning can improve trust and interpretability. Our approach offers a transparent, lightweight alternative to probabilistic models for socially responsible natural language generation.
Authors: Aida Kostikova, Ole P\"utz, Steffen Eger, Olga Sabelfeld, Benjamin Paassen
Abstract: Migration has been a core topic in German political debate, from millions of expellees post World War II over labor migration to refugee movements in the recent past. Studying political speech regarding such wide-ranging phenomena in depth traditionally required extensive manual annotations, limiting the scope of analysis to small subsets of the data. Large language models (LLMs) have the potential to partially automate even complex annotation tasks. We provide an extensive evaluation of a multiple LLMs in annotating (anti-)solidarity subtypes in German parliamentary debates compared to a large set of thousands of human reference annotations (gathered over a year). We evaluate the influence of model size, prompting differences, fine-tuning, historical versus contemporary data; and we investigate systematic errors. Beyond methodological evaluation, we also interpret the resulting annotations from a social science lense, gaining deeper insight into (anti-)solidarity trends towards migrants in the German post-World War II period and recent past. Our data reveals a high degree of migrant-directed solidarity in the postwar period, as well as a strong trend towards anti-solidarity in the German parliament since 2015, motivating further research. These findings highlight the promise of LLMs for political text analysis and the importance of migration debates in Germany, where demographic decline and labor shortages coexist with rising polarization.
Authors: Zhuoqing Song, Peng Sun, Huizhuo Yuan, Quanquan Gu
Abstract: In standard causal attention, each token's query, key, and value (QKV) are static and encode only preceding context. We introduce CAuSal aTtention with Lookahead kEys (CASTLE), an attention mechanism that continually updates each token's keys as the context unfolds. We term these updated keys lookahead keys because they belong to earlier positions yet integrate information from tokens that appear later relative to those positions, while strictly preserving the autoregressive property. Although the mechanism appears sequential, we derive a mathematical equivalence that avoids explicitly materializing lookahead keys at each position and enables efficient parallel training. On language modeling benchmarks, CASTLE consistently outperforms standard causal attention across model scales, reducing validation perplexity and improving performance on a range of downstream tasks.
Authors: David Oprea, Sam Powers
Abstract: We test a new method, which we will abbreviate using the acronym BVM (Basis Vectors Method), in its ability to judge the state changes in images through using language embeddings. We used the MIT-States dataset, containing about 53,000 images, to gather all of our data, which has 225 nouns and 115 adjectives, with each noun having about 9 different adjectives, forming approximately 1000 noun-adjective pairs. For our first experiment, we test our method's ability to determine the state of each noun class separately against other metrics for comparison. These metrics are cosine similarity, dot product, product quantization, binary index, Naive Bayes, and a custom neural network. Among these metrics, we found that our proposed BVM performs the best in classifying the states for each noun. We then perform a second experiment where we try using BVM to determine if it can differentiate adjectives from one another for each adjective separately. We compared the abilities of BVM to differentiate adjectives against the proposed method the MIT-States paper suggests: using a logistic regression model. In the end, we did not find conclusive evidence that our BVM metric could perform better than the logistic regression model at discerning adjectives. Yet, we were able to find evidence for possible improvements to our method; this leads to the chance of increasing our method's accuracy through certain changes in our methodologies.
Authors: Chi-Yang Hsu, Alexander Braylan, Yiheng Su, Omar Alonso, Matthew Lease
Abstract: We motivate and share a new benchmark for instance-level performance prediction of long-form generation tasks having multi-faceted, fine-grained quality metrics. Our task-, model- and metric-agnostic formulation predicts continuous evaluation metric scores given only black-box model inputs and outputs. Beyond predicting point estimates of metric scores, the benchmark also requires inferring prediction intervals to quantify uncertainty around point estimates. Evaluation spans 11 long-form datasets/tasks with multiple LLMs, baselines, and metrics per task. We show that scores can be effectively predicted across long-form generation tasks using as few as 16 training examples. Overall, we introduce a novel and useful task, a valuable benchmark to drive progress, and baselines ready for practical adoption today.
Authors: Sihyun Park
Abstract: Recent advances in large language models (LLMs) have been driven by pretraining, supervised fine tuning (SFT), and alignment tuning. Among these, SFT plays a crucial role in transforming a model 's general knowledge into structured responses tailored to specific tasks. However, there is no clearly established methodology for effective training data selection. Simply increasing the volume of data does not guarantee performance improvements, while preprocessing, sampling, and validation require substantial time and cost. To address this issue, a variety of data selection methods have been proposed. Among them, knowledge based selection approaches identify suitable training data by analyzing the model 's responses. Nevertheless, these methods typically rely on prompt engineering, making them sensitive to variations and incurring additional costs for prompt design. In this study, we propose Knowledge Analysis via Model Internal Representations (KAMIR), a novel approach that overcomes these limitations by analyzing data based on the model 's internal representations. KAMIR computes similarities between the hidden states of each layer (block) and the final hidden states for a given input to assess the data. Unlike prior methods that were largely limited to multiple choice tasks, KAMIR can be applied to a wide range of tasks such as machine reading comprehension and summarization. Moreover, it selects data useful for training based on the model 's familiarity with the input, even with a small dataset and a simple classifier architecture. Experiments across diverse task datasets demonstrate that training with less familiar data leads to better generalization performance.
Authors: Nakyung Lee, Yeongoon Kim, Minhae Oh, Suhwan Kim, Jin Woo Koo, Hyewon Jo, Jungwoo Lee
Abstract: Transformer-based self-attention mechanism serves as the core of modern language models, yet it often suffers from localization, where attentions collapse onto a limited subset of tokens and fail to capture long-range dependencies. To address this issue, we propose Self-Attention One-step Belief Propagation (SAOBP), a refinement framework that injects multi-hop relationships through a belief propagation process. To interpret and quantify these interactions, we introduce Global Token Dependency (GTD) that captures the relative contribution of multihop connections within the attention graph. Empirical results indicate that SAOBP helps prevent entropy collapse in deeper layers and adaptively maintains GTD at task-appropriate levels, thereby supporting improvements in model performance. Importantly, we observe competitive gains in small-scale models, highlighting its potential for improving inference quality in resource-constrained scenarios.
Authors: Yixuan Tang, Yi Yang, Ahmed Abbasi
Abstract: Recent advancements in Large Language Models (LLMs) demonstrate remarkable capabilities across various fields. These developments have led to more direct communication between humans and LLMs in various situations, such as social companionship and psychological support. However, LLMs often exhibit limitations in emotional perception and social competence during real-world conversations. These limitations partly originate from their inability to adapt their communication style and emotional expression to different social and task contexts. In this work, we introduce PersonaFuse, a novel LLM post-training framework that enables LLMs to adapt and express different personalities for varying situations. Inspired by Trait Activation Theory and the Big Five personality model, PersonaFuse employs a Mixture-of-Expert architecture that combines persona adapters with a dynamic routing network, enabling contextual trait expression. Experimental results show that PersonaFuse substantially outperforms baseline models across multiple dimensions of social-emotional intelligence. Importantly, these gains are achieved without sacrificing general reasoning ability or model safety, which remain common limitations of direct prompting and supervised fine-tuning approaches. PersonaFuse also delivers consistent improvements in downstream human-centered applications, such as mental health counseling and review-based customer service. Finally, human preference evaluations against leading LLMs, including GPT-4o and DeepSeek, demonstrate that PersonaFuse achieves competitive response quality despite its comparatively smaller model size. These findings demonstrate that PersonaFuse~offers a theoretically grounded and practical approach for developing social-emotional enhanced LLMs, marking a significant advancement toward more human-centric AI systems.
Authors: Sankalp Tattwadarshi Swain, Anshika Krishnatray, Dhruv Kumar, Jagat Sesh Challa
Abstract: Existing evaluation studies on linguistic competence of large language models (LLM agents) have focused primarily on vocabulary learning, morphological rule induction, syntactic generalization, pragmatic inference, and cross-linguistic transfer. However, none assess whether LLM agents can acquire a language through pattern recognition and interactive feedback, a central feature of human language acquisition. We propose a novel experimental framework in which an LLM agent is evaluated on its ability to acquire and use a newly constructed language (Tinkatongue) in conversation with a bot that understands only Tinkatongue. Our findings show that LLM agents fail to establish a conversation within 100 responses, yet they adopt distinct strategies that mirror human approaches to language learning. The results suggest a new direction for evaluation benchmarks and open pathways to model designs that learn more effectively from interactive feedback.
Authors: Yi-Jie Cheng, Oscar Chew, Yun-Nung Chen
Abstract: Integrating knowledge graphs (KGs) into the reasoning processes of large language models (LLMs) has emerged as a promising approach to mitigate hallucination. However, existing work in this area often relies on proprietary or extremely large models, limiting accessibility and scalability. In this study, we investigate the capabilities of existing integration methods for small language models (SLMs) in KG-based question answering and observe that their performance is often constrained by their limited ability to traverse and reason over knowledge graphs. To address this limitation, we propose leveraging simple and efficient exploration modules to handle knowledge graph traversal in place of the language model itself. Experiment results demonstrate that these lightweight modules effectively improve the performance of small language models on knowledge graph question answering tasks. Source code: https://github.com/yijie-cheng/SLM-ToG/.
Authors: Weichu Liu, Jing Xiong, Yuxuan Hu, Zixuan Li, Minghuan Tan, Ningning Mao, Chenyang Zhao, Zhongwei Wan, Chaofan Tao, Wendong Xu, Hui Shen, Chengming Li, Lingpeng Kong, Ngai Wong
Abstract: Large language models (LLMs) make significant progress in Emotional Intelligence (EI) and long-context understanding. However, existing benchmarks tend to overlook certain aspects of EI in long-context scenarios, especially under realistic, practical settings where interactions are lengthy, diverse, and often noisy. To move towards such realistic settings, we present LongEmotion, a benchmark specifically designed for long-context EI tasks. It covers a diverse set of tasks, including Emotion Classification, Emotion Detection, Emotion QA, Emotion Conversation, Emotion Summary, and Emotion Expression. On average, the input length for these tasks reaches 8,777 tokens, with long-form generation required for Emotion Expression. To enhance performance under realistic constraints, we incorporate Retrieval-Augmented Generation (RAG) and Collaborative Emotional Modeling (CoEM), and compare them with standard prompt-based methods. Unlike conventional approaches, our RAG method leverages both the conversation context and the large language model itself as retrieval sources, avoiding reliance on external knowledge bases. The CoEM method further improves performance by decomposing the task into five stages, integrating both retrieval augmentation and limited knowledge injection. Experimental results show that both RAG and CoEM consistently enhance EI-related performance across most long-context tasks, advancing LLMs toward more practical and real-world EI applications. Furthermore, we conducted a comparative case study experiment on the GPT series to demonstrate the differences among various models in terms of EI. Code is available on GitHub at https://github.com/LongEmotion/LongEmotion, and the project page can be found at https://longemotion.github.io/.
URLs: https://github.com/LongEmotion/LongEmotion,, https://longemotion.github.io/.
Authors: Christian Rene Thelen, Patrick Gustav Blaneck, Tobias Bornheim, Niklas Grieger, Stephan Bialonski
Abstract: Positive, supportive online communication in social media (candy speech) has the potential to foster civility, yet automated detection of such language remains underexplored, limiting systematic analysis of its impact. We investigate how candy speech can be reliably detected in a 46k-comment German YouTube corpus by monolingual and multilingual language models, including GBERT, Qwen3 Embedding, and XLM-RoBERTa. We find that a multilingual XLM-RoBERTa-Large model trained to detect candy speech at the span level outperforms other approaches, ranking first in both binary positive F1: 0.8906) and categorized span-based detection (strict F1: 0.6307) subtasks at the GermEval 2025 Shared Task on Candy Speech Detection. We speculate that span-based training, multilingual capabilities, and emoji-aware tokenizers improved detection performance. Our results demonstrate the effectiveness of multilingual models in identifying positive, supportive language.
Authors: Yiliang Zhou, Di Hu, Tianchu Lyu, Jasmine Dhillon, Alexandra L. Beck, Gelareh Sadigh, Kai Zheng
Abstract: Stigmatizing language results in healthcare inequities, yet there is no universally accepted or standardized lexicon defining which words, terms, or phrases constitute stigmatizing language in healthcare. We conducted a systematic search of the literature to identify existing stigmatizing language lexicons and then analyzed them comparatively to examine: 1) similarities and discrepancies between these lexicons, and 2) the distribution of positive, negative, or neutral terms based on an established sentiment dataset. Our search identified four lexicons. The analysis results revealed moderate semantic similarity among them, and that most stigmatizing terms are related to judgmental expressions by clinicians to describe perceived negative behaviors. Sentiment analysis showed a predominant proportion of negatively classified terms, though variations exist across lexicons. Our findings underscore the need for a standardized lexicon and highlight challenges in defining stigmatizing language in clinical texts.
Authors: Mardiyyah Oduwole, Oluwatosin Olajide, Jamiu Suleiman, Faith Hunja, Busayo Awobade, Fatimo Adebanjo, Comfort Akanni, Chinonyelum Igwe, Peace Ododo, Promise Omoigui, Steven Kolawole, Abraham Owodunni
Abstract: The linguistic diversity across the African continent presents different challenges and opportunities for machine translation. This study explores the effects of data augmentation techniques in improving translation systems in low-resource African languages. We focus on two data augmentation techniques: sentence concatenation with back translation and switch-out, applying them across six African languages. Our experiments show significant improvements in machine translation performance, with a minimum increase of 25\% in BLEU score across all six languages.We provide a comprehensive analysis and highlight the potential of these techniques to improve machine translation systems for low-resource languages, contributing to the development of more robust translation systems for under-resourced languages.
Authors: Saumya Goswami, Siddharth Kurra
Abstract: Detecting content that contradicts or is unsupported by a given source text is a critical challenge for the safe deployment of generative language models. We introduce HALT-RAG, a post-hoc verification system designed to identify hallucinations in the outputs of Retrieval-Augmented Generation (RAG) pipelines. Our flexible and task-adaptable framework uses a universal feature set derived from an ensemble of two frozen, off-the-shelf Natural Language Inference (NLI) models and lightweight lexical signals. These features are used to train a simple, calibrated, and task-adapted meta-classifier. Using a rigorous 5-fold out-of-fold (OOF) training protocol to prevent data leakage and produce unbiased estimates, we evaluate our system on the HaluEval benchmark. By pairing our universal feature set with a lightweight, task-adapted classifier and a precision-constrained decision policy, HALT-RAG achieves strong OOF F1-scores of 0.7756, 0.9786, and 0.7391 on the summarization, QA, and dialogue tasks, respectively. The system's well-calibrated probabilities enable a practical abstention mechanism, providing a reliable tool for balancing model performance with safety requirements.
Authors: Zihan Chen, Lei Shi, Weize Wu, Qiji Zhou, Yue Zhang
Abstract: Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the most informative and representative samples in preparing the demonstrations for LLM modeling. The annotated examples are used to construct a ground-truth retrieval corpus for LLM in-context learning. By sequentially employing three distinct active learning strategies, ALLabel consistently outperforms all baselines under the same annotation budget across three specialized domain datasets. Experimental results also demonstrate that selectively annotating only 5\%-10\% of the dataset with ALLabel can achieve performance comparable to the method annotating the entire dataset. Further analyses and ablation studies verify the effectiveness and generalizability of our proposal.
Authors: Zheng Wu, Heyuan Huang, Xingyu Lou, Xiangmou Qu, Pengzhou Cheng, Zongru Wu, Weiwen Liu, Weinan Zhang, Jun Wang, Zhaoxiang Wang, Zhuosheng Zhang
Abstract: With the rapid progress of multimodal large language models, operating system (OS) agents become increasingly capable of automating tasks through on-device graphical user interfaces (GUIs). However, most existing OS agents are designed for idealized settings, whereas real-world environments often present untrustworthy conditions. To mitigate risks of over-execution in such scenarios, we propose a query-driven human-agent-GUI interaction framework that enables OS agents to decide when to query humans for more reliable task completion. Built upon this framework, we introduce VeriOS-Agent, a trustworthy OS agent trained with a two-stage learning paradigm that falicitate the decoupling and utilization of meta-knowledge. Concretely, VeriOS-Agent autonomously executes actions in normal conditions while proactively querying humans in untrustworthy scenarios. Experiments show that VeriOS-Agent improves the average step-wise success rate by 20.64\% in untrustworthy scenarios over the state-of-the-art, without compromising normal performance. Analysis highlights VeriOS-Agent's rationality, generalizability, and scalability. The codes, datasets and models are available at https://github.com/Wuzheng02/VeriOS.
Authors: Yi Liu, Xiangrong Zhu, Xiangyu Liu, Wei Wei, Wei Hu
Abstract: In a rapidly evolving world where information updates swiftly, knowledge in large language models (LLMs) becomes outdated quickly. Retraining LLMs is not a cost-effective option, making knowledge editing (KE) without modifying parameters particularly necessary. We find that although existing retrieval-augmented generation (RAG)-based KE methods excel at editing simple knowledge, they struggle with KE in multi-hop question answering due to the issue of "edit skipping", which refers to skipping the relevant edited fact in inference. In addition to the diversity of natural language expressions of knowledge, edit skipping also arises from the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory. To address this issue, we propose a novel Iterative Retrieval-Augmented Knowledge Editing method with guided decomposition (IRAKE) through the guidance from single edited facts and entire edited cases. Experimental results demonstrate that IRAKE mitigates the failure of editing caused by edit skipping and outperforms state-of-the-art methods for KE in multi-hop question answering.
Authors: Andrey Sakhovskiy, Elena Tutubalina
Abstract: In recent years, there has been substantial progress in using pretrained Language Models (LMs) on a range of tasks aimed at improving the understanding of biomedical texts. Nonetheless, existing biomedical LLMs show limited comprehension of complex, domain-specific concept structures and the factual information encoded in biomedical Knowledge Graphs (KGs). In this work, we propose BALI (Biomedical Knowledge Graph and Language Model Alignment), a novel joint LM and KG pre-training method that augments an LM with external knowledge by the simultaneous learning of a dedicated KG encoder and aligning the representations of both the LM and the graph. For a given textual sequence, we link biomedical concept mentions to the Unified Medical Language System (UMLS) KG and utilize local KG subgraphs as cross-modal positive samples for these mentions. Our empirical findings indicate that implementing our method on several leading biomedical LMs, such as PubMedBERT and BioLinkBERT, improves their performance on a range of language understanding tasks and the quality of entity representations, even with minimal pre-training on a small alignment dataset sourced from PubMed scientific abstracts.
Authors: Libo Ren, Yee Man Ng, Lifeng Han
Abstract: Efficient communication between patients and clinicians plays an important role in shared decision-making. However, clinical reports are often lengthy and filled with clinical jargon, making it difficult for domain experts to identify important aspects in the document efficiently. This paper presents the methodology we applied in the MultiClinSUM shared task for summarising clinical case documents. We used an Iterative Self-Prompting technique on large language models (LLMs) by asking LLMs to generate task-specific prompts and refine them via example-based few-shot learning. Furthermore, we used lexical and embedding space metrics, ROUGE and BERT-score, to guide the model fine-tuning with epochs. Our submission using perspective-aware ISP on GPT-4 and GPT-4o achieved ROUGE scores (46.53, 24.68, 30.77) and BERTscores (87.84, 83.25, 85.46) for (P, R, F1) from the official evaluation on 3,396 clinical case reports from various specialties extracted from open journals. The high BERTscore indicates that the model produced semantically equivalent output summaries compared to the references, even though the overlap at the exact lexicon level is lower, as reflected in the lower ROUGE scores. This work sheds some light on how perspective-aware ISP (PA-ISP) can be deployed for clinical report summarisation and support better communication between patients and clinicians.
Authors: Xixi Wu, Yanchao Tan, Nan Hou, Ruiyang Zhang, Hong Cheng
Abstract: Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the document into text for processing by Large Language Models (LLMs), but this process strips away critical multi-modal information like figures. While Large Vision-Language Models (LVLMs) address this limitation, their constrained input size makes multi-page document comprehension infeasible. Retrieval-augmented generation (RAG) methods mitigate this by selecting relevant pages, but they rely solely on semantic relevance, ignoring logical connections between pages and the query, which is essential for reasoning. To this end, we propose MoLoRAG, a logic-aware retrieval framework for multi-modal, multi-page document understanding. By constructing a page graph that captures contextual relationships between pages, a lightweight VLM performs graph traversal to retrieve relevant pages, including those with logical connections often overlooked. This approach combines semantic and logical relevance to deliver more accurate retrieval. After retrieval, the top-$K$ pages are fed into arbitrary LVLMs for question answering. To enhance flexibility, MoLoRAG offers two variants: a training-free solution for easy deployment and a fine-tuned version to improve logical relevance checking. Experiments on four DocQA datasets demonstrate average improvements of 9.68% in accuracy over LVLM direct inference and 7.44% in retrieval precision over baselines. Codes and datasets are released at https://github.com/WxxShirley/MoLoRAG.
Authors: Zexuan Li, Hongliang Dai, Piji Li
Abstract: For Relation Extraction (RE), the manual annotation of training data may be prohibitively expensive, since the sentences that contain the target relations in texts can be very scarce and difficult to find. It is therefore beneficial to develop an efficient method that can automatically extract training instances from unlabeled texts for training RE models. Recently, large language models (LLMs) have been adopted in various natural language processing tasks, with RE also benefiting from their advances. However, when leveraging LLMs for RE with predefined relation categories, two key challenges arise. First, in a multi-class classification setting, LLMs often struggle to comprehensively capture the semantics of every relation, leading to suboptimal results. Second, although employing binary classification for each relation individually can mitigate this issue, it introduces significant computational overhead, resulting in impractical time complexity for real-world applications. Therefore, this paper proposes a framework called M-BRe to extract training instances from unlabeled texts for RE. It utilizes three modules to combine the advantages of both of the above classification approaches: Relation Grouping, Relation Extraction, and Label Decision. Extensive experiments confirm its superior capability in discovering high-quality training samples from unlabeled texts for RE.
Authors: Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng, Qian Lou
Abstract: As large language models (LLMs) adapted to sensitive domains such as medicine, their fluency raises safety risks, particularly regarding provenance and accountability. Watermarking embeds detectable patterns to mitigate these risks, yet its reliability in medical contexts remains untested. Existing benchmarks focus on detection-quality tradeoffs, overlooking factual risks under low-entropy settings often exploited by watermarking's reweighting strategy. We propose a medical-focused evaluation workflow that jointly assesses factual accuracy and coherence. Using GPT-Judger and further human validation, we introduce the Factuality-Weighted Score (FWS), a composite metric prioritizing factual accuracy beyond coherence to guide watermarking deployment in medical domains. Our evaluation shows current watermarking methods substantially compromise medical factuality, with entropy shifts degrading medical entity representation. These findings underscore the need for domain-aware watermarking approaches that preserve the integrity of medical content.
Authors: Michele Joshua Maggini, Dhia Merzougui, Rabiraj Bandyopadhyay, Ga\"el Dias, Fabrice Maurel, Pablo Gamallo
Abstract: The spread of fake news, polarizing, politically biased, and harmful content on online platforms has been a serious concern. With large language models becoming a promising approach, however, no study has properly benchmarked their performance across different models, usage methods, and languages. This study presents a comprehensive overview of different Large Language Models adaptation paradigms for the detection of hyperpartisan and fake news, harmful tweets, and political bias. Our experiments spanned 10 datasets and 5 different languages (English, Spanish, Portuguese, Arabic and Bulgarian), covering both binary and multiclass classification scenarios. We tested different strategies ranging from parameter efficient Fine-Tuning of language models to a variety of different In-Context Learning strategies and prompts. These included zero-shot prompts, codebooks, few-shot (with both randomly-selected and diversely-selected examples using Determinantal Point Processes), and Chain-of-Thought. We discovered that In-Context Learning often underperforms when compared to Fine-Tuning a model. This main finding highlights the importance of Fine-Tuning even smaller models on task-specific settings even when compared to the largest models evaluated in an In-Context Learning setup - in our case LlaMA3.1-8b-Instruct, Mistral-Nemo-Instruct-2407 and Qwen2.5-7B-Instruct.
Authors: Decheng Duan, Yingyi Zhang, Jitong Peng, Chengzhi Zhang
Abstract: Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While existing datasets aid model development, most focus on specific publication sections due to domain complexity and the high cost of annotating scientific texts. To address this limitation, we introduce SciNLP - a specialized benchmark for full-text entity and relation extraction in the Natural Language Processing (NLP) domain. The dataset comprises 60 manually annotated full-text NLP publications, covering 7,072 entities and 1,826 relations. Compared to existing research, SciNLP is the first dataset providing full-text annotations of entities and their relationships in the NLP domain. To validate the effectiveness of SciNLP, we conducted comparative experiments with similar datasets and evaluated the performance of state-of-the-art supervised models on this dataset. Results reveal varying extraction capabilities of existing models across academic texts of different lengths. Cross-comparisons with existing datasets show that SciNLP achieves significant performance improvements on certain baseline models. Using models trained on SciNLP, we implemented automatic construction of a fine-grained knowledge graph for the NLP domain. Our KG has an average node degree of 3.2 per entity, indicating rich semantic topological information that enhances downstream applications. The dataset is publicly available at https://github.com/AKADDC/SciNLP.
Authors: Xiaolin Chen, Xuemeng Song, Haokun Wen, Weili Guan, Xiangyu Zhao, Liqiang Nie
Abstract: Textual response generation is pivotal for multimodal \mbox{task-oriented} dialog systems, which aims to generate proper textual responses based on the multimodal context. While existing efforts have demonstrated remarkable progress, there still exist the following limitations: 1) \textit{neglect of unstructured review knowledge} and 2) \textit{underutilization of large language models (LLMs)}. Inspired by this, we aim to fully utilize dual knowledge (\textit{i.e., } structured attribute and unstructured review knowledge) with LLMs to promote textual response generation in multimodal task-oriented dialog systems. However, this task is non-trivial due to two key challenges: 1) \textit{dynamic knowledge type selection} and 2) \textit{intention-response decoupling}. To address these challenges, we propose a novel dual knowledge-enhanced two-stage reasoner by adapting LLMs for multimodal dialog systems (named DK2R). To be specific, DK2R first extracts both structured attribute and unstructured review knowledge from external knowledge base given the dialog context. Thereafter, DK2R uses an LLM to evaluate each knowledge type's utility by analyzing LLM-generated provisional probe responses. Moreover, DK2R separately summarizes the intention-oriented key clues via dedicated reasoning, which are further used as auxiliary signals to enhance LLM-based textual response generation. Extensive experiments conducted on a public dataset verify the superiority of DK2R. We have released the codes and parameters.
Authors: Mihai Nadas, Laura Diosan, Andreea Tomescu, Andrei Piscoran
Abstract: Literary translation has recently gained attention as a distinct and complex task in machine translation research. However, the translation by small open models remains an open problem. We contribute to this ongoing research by introducing TINYFABULIST TRANSLATION FRAMEWORK (TF2), a unified framework for dataset creation, fine tuning, and evaluation in English-Romanian literary translations, centred on the creation and open release of both a compact, fine tuned language model (TF2-12B) and large scale synthetic parallel datasets (DS-TF2-EN-RO-3M and DS-TF2-EN-RO-15K). Building on DS-TF1-EN-3M (TF1), the largest collection of synthetic English fables to date, we address the need for rich, high quality literary datasets in low resource languages such as Romanian. Our pipeline first generates 15k high quality Romanian references from the TF1 pool using a high performing LLM. We then apply a two stage fine tuning process to a 12B parameter open weight model: (i) instruction tuning to capture genre specific narrative style, and (ii) adapter compression for efficient deployment. Evaluation combines corpus level BLEU and a five dimension LLM based rubric (accuracy, fluency, coherence, style, cultural adaptation) to provide a nuanced assessment of translation quality. Results show that our fine tuned model achieves fluency and adequacy competitive with top performing large proprietary models, while being open, accessible, and significantly more cost effective. Alongside the fine tuned model and both datasets, we publicly release all scripts and evaluation prompts. TF2 thus provides an end-to-end, reproducible pipeline for research on cost efficient translation, cross lingual narrative generation, and the broad adoption of open models for culturally significant literary content in low resource settings.
Authors: Jiahui Li, Sean Papay, Roman Klinger
Abstract: The output of large language models (LLM) is unstable, due to both non-determinism of the decoding process as well as to prompt brittleness. While the intrinsic non-determinism of LLM generation may mimic existing uncertainty in human annotations through distributional shifts in outputs, it is largely assumed, yet unexplored, that the prompt brittleness effect is unique to LLMs. This raises the question: do human annotators show similar sensitivity to instruction changes? If so, should prompt brittleness in LLMs be considered problematic? One may alternatively hypothesize that prompt brittleness correctly reflects human annotation variances. To fill this research gap, we systematically compare the effects of prompt modifications on LLMs and identical instruction modifications for human annotators, focusing on the question of whether humans are similarly sensitive to prompt perturbations. To study this, we prompt both humans and LLMs for a set of text classification tasks conditioned on prompt variations. Our findings indicate that both humans and LLMs exhibit increased brittleness in response to specific types of prompt modifications, particularly those involving the substitution of alternative label sets or label formats. However, the distribution of human judgments is less affected by typographical errors and reversed label order than that of LLMs.
Authors: Chengyan Wu, Yiqiang Cai, Yufei Cheng, Yun Xue
Abstract: This paper presents our team's solution to Shared Task 7 of NLPCC-2025, which focuses on sentence-level gender bias detection and mitigation in Chinese. The task aims to promote fairness and controllability in natural language generation by automatically detecting, classifying, and mitigating gender bias. To address this challenge, we adopt a fine-tuning approach based on large language models (LLMs), efficiently adapt to the bias detection task via Low-Rank Adaptation (LoRA). In terms of data processing, we construct a more balanced training set to alleviate class imbalance and introduce heterogeneous samples from multiple sources to enhance model generalization. For the detection and classification sub-tasks, we employ a majority voting strategy that integrates outputs from multiple expert models to boost performance. Additionally, to improve bias generation detection and mitigation, we design a multi-temperature sampling mechanism to capture potential variations in bias expression styles. Experimental results demonstrate the effectiveness of our approach in bias detection, classification, and mitigation. Our method ultimately achieves an average score of 47.90%, ranking fourth in the shared task.
Authors: Donya Rooein, Vil\'em Zouhar, Debora Nozza, Dirk Hovy
Abstract: Stories play a pivotal role in human communication, shaping beliefs and morals, particularly in children. As parents increasingly rely on large language models (LLMs) to craft bedtime stories, the presence of cultural and gender stereotypes in these narratives raises significant concerns. To address this issue, we present Biased Tales, a comprehensive dataset designed to analyze how biases influence protagonists' attributes and story elements in LLM-generated stories. Our analysis uncovers striking disparities. When the protagonist is described as a girl (as compared to a boy), appearance-related attributes increase by 55.26%. Stories featuring non-Western children disproportionately emphasize cultural heritage, tradition, and family themes far more than those for Western children. Our findings highlight the role of sociocultural bias in making creative AI use more equitable and diverse.
Authors: Tuo Wang, Adithya Kulkarni, Tyler Cody, Peter A. Beling, Yujun Yan, Dawei Zhou
Abstract: Uncertainty estimation is essential for enhancing the reliability of Large Language Models (LLMs), particularly in high-stakes applications. Existing methods often overlook semantic dependencies, relying on token-level probability measures that fail to capture structural relationships within the generated text. We propose GENUINE: Graph ENhanced mUlti-level uncertaINty Estimation for Large Language Models, a structure-aware framework that leverages dependency parse trees and hierarchical graph pooling to refine uncertainty quantification. By incorporating supervised learning, GENUINE effectively models semantic and structural relationships, improving confidence assessments. Extensive experiments across NLP tasks show that GENUINE achieves up to 29% higher AUROC than semantic entropy-based approaches and reduces calibration errors by over 15%, demonstrating the effectiveness of graph-based uncertainty modeling. The code is available at https://github.com/ODYSSEYWT/GUQ.
Authors: Lukas Haas, Gal Yona, Giovanni D'Antonio, Sasha Goldshtein, Dipanjan Das
Abstract: We introduce SimpleQA Verified, a 1,000-prompt benchmark for evaluating Large Language Model (LLM) short-form factuality based on OpenAI's SimpleQA. It addresses critical limitations in OpenAI's benchmark, including noisy and incorrect labels, topical biases, and question redundancy. SimpleQA Verified was created through a rigorous multi-stage filtering process involving de-duplication, topic balancing, and source reconciliation to produce a more reliable and challenging evaluation set, alongside improvements in the autorater prompt. On this new benchmark, Gemini 2.5 Pro achieves a state-of-the-art F1-score of 55.6, outperforming other frontier models, including GPT-5. This work provides the research community with a higher-fidelity tool to track genuine progress in parametric model factuality and to mitigate hallucinations. The benchmark dataset, evaluation code, and leaderboard are available at: https://www.kaggle.com/benchmarks/deepmind/simpleqa-verified.
URLs: https://www.kaggle.com/benchmarks/deepmind/simpleqa-verified.
Authors: Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, Xinyu Yang, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang, Dong Yu
Abstract: Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose \textbf{Parallel-R1}, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model's thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a \textbf{mid-training exploration scaffold}, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25. Our model, data, and code will be open-source at https://github.com/zhengkid/Parallel-R1.
Authors: Xiaomeng Hu, Fei Huang, Chenhan Yuan, Junyang Lin, Tsung-Yi Ho
Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring the safety of their outputs during decoding has become a critical challenge. However, existing decoding-time interventions, such as Contrastive Decoding, often force a severe trade-off between safety and response quality. In this work, we propose CARE, a novel framework for decoding-time safety alignment that integrates three key components: (1) a guard model for real-time safety monitoring, enabling detection of potentially unsafe content; (2) a rollback mechanism with a token buffer to correct unsafe outputs efficiently at an earlier stage without disrupting the user experience; and (3) a novel introspection-based intervention strategy, where the model generates self-reflective critiques of its previous outputs and incorporates these reflections into the context to guide subsequent decoding steps. The framework achieves a superior safety-quality trade-off by using its guard model for precise interventions, its rollback mechanism for timely corrections, and our novel introspection method for effective self-correction. Experimental results demonstrate that our framework achieves a superior balance of safety, quality, and efficiency, attaining a low harmful response rate and minimal disruption to the user experience while maintaining high response quality.
Authors: Srihari Bandraupalli, Anupam Purwar
Abstract: Open-source Vision-Language Models show immense promise for enterprise applications, yet a critical disconnect exists between academic evaluation and enterprise deployment requirements. Current benchmarks rely heavily on multiple-choice questions and synthetic data, failing to capture the complexity of real-world business applications like social media content analysis. This paper introduces VLM-in-the-Wild (ViLD), a comprehensive framework to bridge this gap by evaluating VLMs on operational enterprise requirements. We define ten business-critical tasks: logo detection, OCR, object detection, human presence and demographic analysis, human activity and appearance analysis, scene detection, camera perspective and media quality assessment, dominant colors, comprehensive description, and NSFW detection. To this framework, we bring an innovative BlockWeaver Algorithm that solves the challenging problem of comparing unordered, variably-grouped OCR outputs from VLMs without relying on embeddings or LLMs, achieving remarkable speed and reliability. To demonstrate efficacy of ViLD, we constructed a new benchmark dataset of 7,500 diverse samples, carefully stratified from a corpus of one million real-world images and videos. ViLD provides actionable insights by combining semantic matching (both embedding-based and LLM-as-a-judge approaches), traditional metrics, and novel methods to measure the completeness and faithfulness of descriptive outputs. By benchmarking leading open-source VLMs (Qwen, MIMO, and InternVL) against a powerful proprietary baseline as per ViLD framework, we provide one of the first industry-grounded, task-driven assessment of VLMs capabilities, offering actionable insights for their deployment in enterprise environments.
Authors: Kapil Madan
Abstract: This paper introduces ArGen (Auto-Regulation of Generative AI systems), a framework for aligning Large Language Models (LLMs) with complex sets of configurable, machine-readable rules spanning ethical principles, operational safety protocols, and regulatory compliance standards. Moving beyond just preference-based alignment, ArGen is designed to ensure LLMs adhere to these multifaceted policies through a novel synthesis of principle-based automated reward scoring, Group Relative Policy Optimisation (GRPO), and an Open Policy Agent (OPA) inspired governance layer. This approach provides the technical foundation for achieving and demonstrating compliance with diverse and nuanced governance requirements. To showcase the framework's capability to operationalize a deeply nuanced and culturally-specific value system, we present an in-depth case study: the development of a medical AI assistant guided by principles from Dharmic ethics (such as Ahimsa and Dharma), as derived from texts like the Bhagavad Gita. This challenging application demonstrates ArGen's adaptability, achieving a 70.9% improvement in domain-scope adherence over the baseline. Through our open-source repository, we show that ArGen's methodology offers a path to 'Governable Al' systems that are technically proficient, ethically robust, and verifiably compliant for safe deployment in diverse global contexts.
Authors: Andrew Kiruluta, Priscilla Burity
Abstract: We introduce Spectral NSR, a fully spectral neuro-symbolic reasoning framework that embeds logical rules as spectral templates and performs inference directly in the graph spectral domain. By leveraging graph signal processing (GSP) and frequency-selective filters grounded in the Laplacian eigenstructure of knowledge graphs, the architecture unifies the interpretability of symbolic reasoning with the scalability and adaptability of spectral learning. Beyond the core formulation, we incorporate a comprehensive set of extensions, including dynamic graph and basis learning, rational and diffusion filters for sharper spectral selectivity, mixture-of-spectral-experts for modular specialization, proof-guided training with spectral curricula, and uncertainty quantification for calibrated confidence. Additional enhancements such as large language model coupling, co-spectral transfer alignment, adversarial robustness, efficient GPU kernels, generalized Laplacians, and causal interventions further expand the versatility of the framework. Empirical evaluation on state-of-the-art reasoning benchmarks such as ProofWriter and CLUTRR demonstrates that Spectral NSR achieves superior accuracy, faster inference, improved robustness to adversarial perturbations, and higher interpretability compared to leading baselines including transformers, message-passing neural networks, and neuro-symbolic logic programming systems. Spectral attribution and proof-band agreement analyses confirm that model decisions align closely with symbolic proof structures, while transfer experiments validate effective domain adaptation through co-spectral alignment. These results establish Spectral NSR as a scalable and principled foundation for the next generation of reasoning systems, offering transparency, robustness, and generalization beyond conventional approaches.
Authors: Yinheng Li, Hailey Hultquist, Justin Wagle, Kazuhito Koishida
Abstract: Graphical user interface (GUI) agents have advanced rapidly but still struggle with complex tasks involving novel UI elements, long-horizon actions, and personalized trajectories. In this work, we introduce Instruction Agent, a GUI agent that leverages expert demonstrations to solve such tasks, enabling completion of otherwise difficult workflows. Given a single demonstration, the agent extracts step-by-step instructions and executes them by strictly following the trajectory intended by the user, which avoids making mistakes during execution. The agent leverages the verifier and backtracker modules further to improve robustness. Both modules are critical to understand the current outcome from each action and handle unexpected interruptions(such as pop-up windows) during execution. Our experiments show that Instruction Agent achieves a 60% success rate on a set of tasks in OSWorld that all top-ranked agents failed to complete. The Instruction Agent offers a practical and extensible framework, bridging the gap between current GUI agents and reliable real-world GUI task automation.
Authors: Sania Sinha, Tanawan Premsri, Danial Kamali, Parisa Kordjamshidi
Abstract: Neurosymbolic (NeSy) frameworks combine neural representations and learning with symbolic representations and reasoning. Combining the reasoning capacities, explainability, and interpretability of symbolic processing with the flexibility and power of neural computing allows us to solve complex problems with more reliability while being data-efficient. However, this recently growing topic poses a challenge to developers with its learning curve, lack of user-friendly tools, libraries, and unifying frameworks. In this paper, we characterize the technical facets of existing NeSy frameworks, such as the symbolic representation language, integration with neural models, and the underlying algorithms. A majority of the NeSy research focuses on algorithms instead of providing generic frameworks for declarative problem specification to leverage problem solving. To highlight the key aspects of Neurosymbolic modeling, we showcase three generic NeSy frameworks - \textit{DeepProbLog}, \textit{Scallop}, and \textit{DomiKnowS}. We identify the challenges within each facet that lay the foundation for identifying the expressivity of each framework in solving a variety of problems. Building on this foundation, we aim to spark transformative action and encourage the community to rethink this problem in novel ways.
Authors: Anatoly A. Krasnovsky
Abstract: Mechanistic interpretability has identified functional subgraphs within large language models (LLMs), known as Transformer Circuits (TCs), that appear to implement specific algorithms. Yet we lack a formal, single-pass way to quantify when an active circuit is behaving coherently and thus likely trustworthy. Building on prior systems-theoretic proposals, we specialize a sheaf/cohomology and causal emergence perspective to TCs and introduce the Effective-Information Consistency Score (EICS). EICS combines (i) a normalized sheaf inconsistency computed from local Jacobians and activations, with (ii) a Gaussian EI proxy for circuit-level causal emergence derived from the same forward state. The construction is white-box, single-pass, and makes units explicit so that the score is dimensionless. We further provide practical guidance on score interpretation, computational overhead (with fast and exact modes), and a toy sanity-check analysis. Empirical validation on LLM tasks is deferred.
Authors: Haike Xu, Tong Chen
Abstract: The widely used retrieve-and-rerank pipeline faces two critical limitations: they are constrained by the initial retrieval quality of the top-k documents, and the growing computational demands of LLM-based rerankers restrict the number of documents that can be effectively processed. We introduce Reranker-Guided-Search (RGS), a novel approach that bypasses these limitations by directly retrieving documents according to reranker preferences rather than following the traditional sequential reranking method. Our method uses a greedy search on proximity graphs generated by approximate nearest neighbor algorithms, strategically prioritizing promising documents for reranking based on document similarity. Experimental results demonstrate substantial performance improvements across multiple benchmarks: 3.5 points on BRIGHT, 2.9 on FollowIR, and 5.1 on M-BEIR, all within a constrained reranker budget of 100 documents. Our analysis suggests that, given a fixed pair of embedding and reranker models, strategically selecting documents to rerank can significantly improve retrieval accuracy under limited reranker budget.
Authors: Quinten Steenhuis
Abstract: Each year millions of people seek help for their legal problems by calling a legal aid program hotline, walking into a legal aid office, or using a lawyer referral service. The first step to match them to the right help is to identify the legal problem the applicant is experiencing. Misdirection has consequences. Applicants may miss a deadline, experience physical abuse, lose housing or lose custody of children while waiting to connect to the right legal help. We introduce and evaluate the FETCH classifier for legal issue classification and describe two methods for improving accuracy: a hybrid LLM/ML ensemble classification method, and the automatic generation of follow-up questions to enrich the initial problem narrative. We employ a novel data set of 419 real-world queries to a nonprofit lawyer referral service. Ultimately, we show classification accuracy (hits@2) of 97.37\% using a mix of inexpensive models, exceeding the performance of the current state-of-the-art GPT-5 model. Our approach shows promise in significantly reducing the cost of guiding users of the legal system to the right resource for their problem while achieving high accuracy.
Authors: Khushiyant
Abstract: Text generating capabilities have undergone a substantial transformation with the introduction of large language models (LLMs). Electroencephalography (EEG)-based text production is still difficult, though, because it requires a lot of data and processing power. This paper introduces a new method that combines the use of the Gemma 2B LLM with a classifier-LLM architecture to incorporate a Recurrent Neural Network (RNN) encoder. Our approach drastically lowers the amount of data and compute power needed while achieving performance close to that of cutting-edge methods. Notably, compared to current methodologies, our methodology delivers an overall performance improvement of 10%. The suggested architecture demonstrates the possibility of effective transfer learning for EEG-based text production, remaining strong and functional even in the face of data limits. This work highlights the potential of integrating LLMs with EEG decoding to improve assistive technologies and improve independence and communication for those with severe motor limitations. Our method pushes the limits of present capabilities and opens new paths for research and application in brain-computer interfaces by efficiently using the strengths of pre-trained language models. This makes EEG-based text production more accessible and efficient.
Authors: Julian Killingback, Hamed Zamani
Abstract: Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contrast, have not yet seen such capable general-purpose models emerge. To achieve this goal, retrieval models must be able to perform complex retrieval tasks, where queries contain multiple parts, constraints, or requirements in natural language. These tasks represent a natural progression from the simple, single-aspect queries that are used in the vast majority of existing, commonly used evaluation sets. Complex queries naturally arise as people expect search systems to handle more specific and often ambitious information requests, as is demonstrated by how people use LLM-based information systems. Despite the growing desire for retrieval models to expand their capabilities in complex retrieval tasks, there exist limited resources to assess the ability of retrieval models on a comprehensive set of diverse complex tasks. The few resources that do exist feature a limited scope and often lack realistic settings making it hard to know the true capabilities of retrieval models on complex real-world retrieval tasks. To address this shortcoming and spur innovation in next-generation retrieval models, we construct a diverse and realistic set of complex retrieval tasks and benchmark a representative set of state-of-the-art retrieval models. Additionally, we explore the impact of LLM-based query expansion and rewriting on retrieval quality. Our results show that even the best models struggle to produce high-quality retrieval results with the highest average nDCG@10 of only 0.346 and R@100 of only 0.587 across all tasks. Although LLM augmentation can help weaker models, the strongest model has decreased performance across all metrics with all rewriting techniques.
Authors: Jeff Shen, Lindsay Smith
Abstract: We present cryptogram solving as an ideal testbed for studying neural network generalization in combinatorially complex domains. In this task, models must decrypt text encoded with substitution ciphers, choosing from 26! possible mappings without explicit access to the cipher. We develop ALICE (an Architecture for Learning Interpretable Cryptogram dEcipherment): a simple encoder-only Transformer that sets a new state-of-the-art for both accuracy and speed on this decryption problem. Surprisingly, ALICE generalizes to unseen ciphers after training on only ${\sim}1500$ unique ciphers, a minute fraction ($3.7 \times 10^{-24}$) of the possible cipher space. To enhance interpretability, we introduce a novel bijective decoding head that explicitly models permutations via the Gumbel-Sinkhorn method, enabling direct extraction of learned cipher mappings. Through early exit analysis, we reveal how ALICE progressively refines its predictions in a way that appears to mirror common human strategies for this task: early layers employ frequency-based heuristics, middle layers form word structures, and final layers correct individual characters. Our architectural innovations and analysis methods extend beyond cryptograms to any domain with bijective mappings and combinatorial structure, offering new insights into neural network generalization and interpretability.
Authors: Jakub Grudzien Kuba, Mengting Gu, Qi Ma, Yuandong Tian, Vijai Mohan
Abstract: Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fundamental bottleneck: the need for ever more data from which models can continue to learn. In this work, we propose a reinforcement learning approach that removes this dependency by enabling models to improve without additional data. Our method leverages a game-theoretic framework of self-play, where a model's capabilities are cast as performance in a competitive game and stronger policies emerge by having the model play against itself - a process we call Language Self-Play (LSP). Experiments with Llama-3.2-3B-Instruct on instruction-following benchmarks show that pretrained models can not only enhance their performance on challenging tasks through self-play alone, but can also do so more effectively than data-driven baselines.
Authors: Xudong Lu, Zhi Zheng, Yi Wan, Yongxiang Yao, Annan Wang, Renrui Zhang, Panwang Xia, Qiong Wu, Qingyun Li, Weifeng Lin, Xiangyu Zhao, Xue Yang, Hongsheng Li
Abstract: Cross-View Geo-Localization (CVGL) focuses on identifying correspondences between images captured from distinct perspectives of the same geographical location. However, existing CVGL approaches are typically restricted to a single view or modality, and their direct visual matching strategy lacks interpretability: they merely predict whether two images correspond, without explaining the rationale behind the match. In this paper, we present GLEAM-C, a foundational CVGL model that unifies multiple views and modalities-including UAV imagery, street maps, panoramic views, and ground photographs-by aligning them exclusively with satellite imagery. Our framework enhances training efficiency through optimized implementation while achieving accuracy comparable to prior modality-specific CVGL models through a two-phase training strategy. Moreover, to address the lack of interpretability in traditional CVGL methods, we leverage the reasoning capabilities of multimodal large language models (MLLMs) to propose a new task, GLEAM-X, which combines cross-view correspondence prediction with explainable reasoning. To support this task, we construct a bilingual benchmark using GPT-4o and Doubao-1.5-Thinking-Vision-Pro to generate training and testing data. The test set is further refined through detailed human revision, enabling systematic evaluation of explainable cross-view reasoning and advancing transparency and scalability in geo-localization. Together, GLEAM-C and GLEAM-X form a comprehensive CVGL pipeline that integrates multi-modal, multi-view alignment with interpretable correspondence analysis, unifying accurate cross-view matching with explainable reasoning and advancing Geo-Localization by enabling models to better Explain And Match. Code and datasets used in this work will be made publicly accessible at https://github.com/Lucky-Lance/GLEAM.
Authors: Anjiang Wei, Tianran Sun, Yogesh Seenichamy, Hang Song, Anne Ouyang, Azalia Mirhoseini, Ke Wang, Alex Aiken
Abstract: GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating large language model (LLM) training and serving, yet attaining high performance typically requires extensive manual tuning. Compiler-based systems reduce some of this burden, but still demand substantial manual design and engineering effort. Recently, researchers have explored using LLMs for GPU kernel generation, though prior work has largely focused on translating high-level PyTorch modules into CUDA code. In this work, we introduce Astra, the first LLM-based multi-agent system for GPU kernel optimization. Unlike previous approaches, Astra starts from existing CUDA implementations extracted from SGLang, a widely deployed framework for serving LLMs, rather than treating PyTorch modules as the specification. Within Astra, specialized LLM agents collaborate through iterative code generation, testing, profiling, and planning to produce kernels that are both correct and high-performance. On kernels from SGLang, Astra achieves an average speedup of 1.32x using zero-shot prompting with OpenAI o4-mini. A detailed case study further demonstrates that LLMs can autonomously apply loop transformations, optimize memory access patterns, exploit CUDA intrinsics, and leverage fast math operations to yield substantial performance gains. Our work highlights multi-agent LLM systems as a promising new paradigm for GPU kernel optimization.
Authors: Gokul Karthik Kumar, Rishabh Saraf, Ludovick Lepauloux, Abdul Muneer, Billel Mokeddem, Hakim Hacid
Abstract: Large language models (LLMs) have transformed NLP, yet their integration with audio remains underexplored -- despite audio's centrality to human communication. We introduce Falcon3-Audio, a family of Audio-Language Models (ALMs) built on instruction-tuned LLMs and Whisper encoders. Using a remarkably small amount of public audio data -- less than 30K hours (5K unique) -- Falcon3-Audio-7B matches the best reported performance among open-weight models on the MMAU benchmark, with a score of 64.14, matching R1-AQA, while distinguishing itself through superior data and parameter efficiency, single-stage training, and transparency. Notably, our smallest 1B model remains competitive with larger open models ranging from 2B to 13B parameters. Through extensive ablations, we find that common complexities -- such as curriculum learning, multiple audio encoders, and intricate cross-attention connectors -- are not required for strong performance, even compared to models trained on over 500K hours of data.
Authors: Arun Verma, Zhaoxuan Wu, Zijian Zhou, Xiaoqiang Lin, Zhiliang Chen, Rachael Hwee Ling Sim, Rui Qiao, Jingtan Wang, Nhung Bui, Xinyuan Niu, Wenyang Hu, Gregory Kang Ruey Lau, Zi-Yu Khoo, Zitong Zhao, Xinyi Xu, Apivich Hemachandra, See-Kiong Ng, Bryan Kian Hsiang Low
Abstract: Large Language Models (LLMs) are large-scale pretrained models that have achieved remarkable success across diverse domains. These successes have been driven by unprecedented complexity and scale in both data and computations. However, due to the high costs of training such models, brute-force trial-and-error approaches to improve LLMs are not feasible. Inspired by the success of inverse problems in uncovering fundamental scientific laws, this position paper advocates that inverse problems can also efficiently uncover scaling laws that guide the building of LLMs to achieve the desirable performance with significantly better cost-effectiveness.
Authors: Boammani Aser Lompo, Marc Haraoui
Abstract: Visual reasoning over structured data such as tables is a critical capability for modern vision-language models (VLMs), yet current benchmarks remain limited in scale, diversity, or reasoning depth, especially when it comes to rendered table images. Addressing this gap, we introduce Visual-TableQA, a large-scale, open-domain multimodal dataset specifically designed to evaluate and enhance visual reasoning over complex tabular data. Our generation pipeline is modular, scalable, and fully autonomous, involving multiple reasoning LLMs collaborating across distinct roles: generation, validation, and inspiration. Visual-TableQA comprises 2.5k richly structured LaTeX-rendered tables and 6k reasoning-intensive QA pairs, all produced at a cost of under USD 100. To promote diversity and creativity, our pipeline performs multi-model collaborative data generation via cross-model prompting ('inspiration') and LLM-jury filtering. Stronger models seed layouts and topics that weaker models elaborate, collectively distilling diverse reasoning patterns and visual structures into the dataset. Empirical results show that models fine-tuned on Visual-TableQA generalize robustly to external benchmarks, outperforming several proprietary models despite the dataset's synthetic nature. The full pipeline and resources are publicly available at https://github.com/AI-4-Everyone/Visual-TableQA.
Authors: Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, Hengshuang Zhao
Abstract: Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited number of interaction turns, making them inadequate for difficult tasks that require trial-and-error exploration. In this work, we address this limitation by scaling up tool-based interactions and introduce Mini-o3, a system that executes deep, multi-turn reasoning -- spanning tens of steps -- and achieves state-of-the-art performance on challenging visual search tasks. Our recipe for reproducing OpenAI o3-style behaviors comprises three key components. First, we construct the Visual Probe Dataset, a collection of thousands of challenging visual search problems designed for exploratory reasoning. Second, we develop an iterative data collection pipeline to obtain cold-start trajectories that exhibit diverse reasoning patterns, including depth-first search, trial-and-error, and goal maintenance. Third, we propose an over-turn masking strategy that prevents penalization of over-turn responses (those that hit the maximum number of turns) during reinforcement learning, thereby balancing training-time efficiency with test-time scalability. Despite training with an upper bound of only six interaction turns, our model generates trajectories that naturally scale to tens of turns at inference time, with accuracy improving as the number of turns increases. Extensive experiments demonstrate that Mini-o3 produces rich reasoning patterns and deep thinking paths, effectively solving challenging visual search problems.
Authors: Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
Abstract: Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs) holds significant potential in enhancing their user experiences. Previous approaches either relied on fine-tuning LLMs on specific corpora or required manually crafted prompts to evoke specific personalities from LLMs. However, the former is inefficient and costly, while the latter cannot precisely manipulate personality traits at a fine-grained level. To address these challenges, we propose UPLex, a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM's personality traits. UPL can be constructed from a newly built situational judgment test dataset in an unsupervised fashion, and used to modulate the personality expression of LLMs by dynamically altering their predicted probability of upcoming words in a pluggable fashion. Extensive experimentation demonstrates the remarkable effectiveness and pluggability of our method for fine-grained manipulation of LLMs' personalities.
Authors: Emily Cheng, Carmen Amo Alonso
Abstract: The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To achieve this, we use a common model of concept semantics as linearly represented in an LM's latent space. In particular, we take the view that natural language generation traces a trajectory in this continuous semantic space, realized by the language model's hidden activations. This view permits a control-theoretic treatment of text generation in latent space, in which we propose a lightweight, gradient-free intervention that dynamically steers trajectories away from regions corresponding to undesired meanings. In particular, we propose to directly intervene the activations of the token that is being generated in embedding space in an online fashion. Crucially, we do not simply steer activations towards a desirable region. Instead, our method relies on classical techniques from control theory to precisely control activations in a context-dependent way, and guarantees that they are brought into a specific pre-defined region of embedding space that corresponds to allowed semantics. Our intervention is computed in closed-form according to an optimal controller formulation, minimally impacting generation time. This control of the activations in embedding space allows for fine-grained steering of attributes of the generated sequence. We demonstrate the effectiveness of our approach on different objectives -- toxicity avoidance and sentiment control -- while maintaining text quality.
Authors: Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin
Abstract: Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content still remains obscure to humans, underscoring the necessity of understanding the causality between input and output pairs. Existing works for providing prompt-specific explanation often confine model output to be classification or next-word prediction. Few initial attempts aiming to explain the entire language generation often treat input prompt texts independently, ignoring their combinatorial effects on the follow-up generation. In this study, we introduce a counterfactual explanation framework based on Joint Prompt Attribution, JoPA, which aims to explain how a few prompt texts collaboratively influences the LLM's complete generation. Particularly, we formulate the task of prompt attribution for generation interpretation as a combinatorial optimization problem, and introduce a probabilistic algorithm to search for the casual input combination in the discrete space. We define and utilize multiple metrics to evaluate the produced explanations, demonstrating both the faithfulness and efficiency of our framework.
Authors: Qikai Wei, Mingzhi Yang, Jinqiang Wang, Wenwei Mao, Jiabo Xu, Huansheng Ning
Abstract: Recently, large language models (LLMs) have demonstrated their effectiveness in various natural language processing (NLP) tasks. However, the lack of tourism knowledge limits the performance of LLMs in tourist attraction presentations and travel planning. To address this challenge, we constructed a supervised fine-tuning dataset for the Chinese culture and tourism domain, named Cultour. This dataset consists of three parts: tourism knowledge base data, travelogues data, and tourism QA data. Additionally, we propose CTourLLM, a Qwen-based model supervised fine-tuned with Cultour, to improve the quality of information about attractions and travel planning. To evaluate the performance of CTourLLM, we proposed a human evaluation criterion named RRA (Relevance, Readability, Availability), and employed both automatic and human evaluation. The experimental results demonstrate that CTourLLM outperforms ChatGPT, achieving an improvement of 1.21 in BLEU-1 and 1.54 in Rouge-L, thereby validating the effectiveness of the response outcomes. Our proposed Cultour is accessible at https://github.com/mrweiqk/Cultour.
Authors: Wei Wu, Zhuoshi Pan, Chao Wang, Liyi Chen, Yunchu Bai, Tianfu Wang, Kun Fu, Zheng Wang, Hui Xiong
Abstract: Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challenges: performance degradation due to sequence lengths out-of-distribution, and excessively long inference times caused by the quadratic computational complexity of attention. These issues limit LLMs in long-context scenarios. In this paper, we propose Dynamic Token-Level KV Cache Selection (TokenSelect), a training-free method for efficient and accurate long-context inference. TokenSelect builds upon the observation of non-contiguous attention sparsity, using QK dot products to measure per-head KV Cache criticality at token-level. By per-head soft voting mechanism, TokenSelect selectively involves a few critical KV cache tokens in attention calculation without sacrificing accuracy. To further accelerate TokenSelect, we design the Selection Cache based on observations of consecutive Query similarity and implemented the efficient Paged Dot Product Kernel, significantly reducing the selection overhead. A comprehensive evaluation of TokenSelect demonstrates up to $23.84\times$ speedup in attention computation and up to $2.28\times$ acceleration in end-to-end latency, while providing superior performance compared to state-of-the-art long-context inference methods.
Authors: Libo Zhang, Zhaoning Zhang, Baizhou Xu, Rui Li, Zhiliang Tian, Songzhu Mei, Dongsheng Li
Abstract: With the continuous advancement in the performance of large language models (LLMs), their demand for computational resources and memory has significantly increased, which poses major challenges for efficient inference on consumer-grade devices and legacy servers. These devices typically feature relatively weaker GPUs and stronger CPUs. Although techniques such as parameter offloading and partial offloading can alleviate GPU memory pressure to some extent, their effectiveness is limited due to communication latency and suboptimal hardware resource utilization. To address this issue, we propose Dovetail, a lossless inference acceleration method that leverages the complementary characteristics of heterogeneous devices and the advantages of speculative decoding. Dovetail deploys a draft model on the GPU to perform preliminary predictions, while a target model running on the CPU validates these outputs. By reducing the granularity of data transfer, Dovetail significantly minimizes communication overhead. To further improve efficiency, we optimize the draft model specifically for heterogeneous hardware environments by reducing the number of draft tokens to lower parallel verification latency, increasing model depth to enhance predictive capabilities, and introducing a Dynamic Gating Fusion (DGF) mechanism to improve the integration of feature and embedding information. We conduct comprehensive evaluations of Dovetail across various consumer-grade GPUs, covering multiple tasks and mainstream models. Experimental results on 13B models demonstrate that Dovetail achieves inference speedups ranging from 1.79x to 10.1x across different devices, while maintaining consistency and stability in the distribution of generated texts.
Authors: Danrui Li, Sen Zhang, Sam S. Sohn, Kaidong Hu, Muhammad Usman, Mubbasir Kapadia
Abstract: The prototyping of computer games, particularly card games, requires extensive human effort in creative ideation and gameplay evaluation. Recent advances in Large Language Models (LLMs) offer opportunities to automate and streamline these processes. However, it remains challenging for LLMs to design novel game mechanics beyond existing databases, generate consistent gameplay environments, and develop scalable gameplay AI for large-scale evaluations. This paper addresses these challenges by introducing a comprehensive automated card game prototyping framework. The approach highlights a graph-based indexing method for generating novel game variations, an LLM-driven system for consistent game code generation validated by gameplay records, and a gameplay AI constructing method that uses an ensemble of LLM-generated heuristic functions optimized through self-play. These contributions aim to accelerate card game prototyping, reduce human labor, and lower barriers to entry for game developers. For code repo visit this http URL https://github.com/danruili/Cardiverse
Authors: Zilu Dong, Xiangqing Shen, Rui Xia
Abstract: As large language models continue to scale up, knowledge editing techniques that modify models' internal knowledge without full retraining have gained significant attention. MEMIT, a prominent batch editing algorithm, stands out for its capability to perform mass knowledge modifications. However, we uncover that MEMIT's editing efficacy significantly deteriorates when processing batches containing multiple edits sharing the same subject. Our analysis reveals this stems from MEMIT's key value modeling framework: identical keys (derived from the shared subject) are forced to represent different values (corresponding to different knowledge), resulting in update conflicts during editing. Addressing this issue, we propose MEMIT-Merge, an enhanced approach that merges value computation processes for facts sharing the same subject, effectively resolving the performance degradation in samesubject batch editing scenarios. Experimental results demonstrate that when MEMIT's edit success rate drops to around 50% at larger batch sizes, MEMIT-Merge maintains a success rate exceeding 90%, showcasing remarkable robustness to subject entity collisions. The code is available at https://github.com/NUSTM/ MEMIT-Merge.
Authors: Chengyan Wu, Bolei Ma, Yihong Liu, Zheyu Zhang, Ningyuan Deng, Yanshu Li, Baolan Chen, Yi Zhang, Yun Xue, Barbara Plank
Abstract: Aspect-based sentiment analysis (ABSA) is a crucial task in information extraction and sentiment analysis, aiming to identify aspects with associated sentiment elements in text. However, existing ABSA datasets are predominantly English-centric, limiting the scope for multilingual evaluation and research. To bridge this gap, we present M-ABSA, a comprehensive dataset spanning 7 domains and 21 languages, making it the most extensive multilingual parallel dataset for ABSA to date. Our primary focus is on triplet extraction, which involves identifying aspect terms, aspect categories, and sentiment polarities. The dataset is constructed through an automatic translation process with human review to ensure quality. We perform extensive experiments using various baselines to assess performance and compatibility on M-ABSA. Our empirical findings highlight that the dataset enables diverse evaluation tasks, such as multilingual and multi-domain transfer learning, and large language model evaluation, underscoring its inclusivity and its potential to drive advancements in multilingual ABSA research.
Authors: Jingbiao Mei, Jinghong Chen, Guangyu Yang, Weizhe Lin, Bill Byrne
Abstract: Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hateful meme detection, they face notable challenges like sub-optimal performance and limited out-of-domain generalization capabilities. Recent studies further reveal the limitations of both supervised fine-tuning (SFT) and in-context learning when applied to LMMs in this setting. To address these issues, we propose a robust adaptation framework for hateful meme detection that enhances in-domain accuracy and cross-domain generalization while preserving the general vision-language capabilities of LMMs. Analysis reveals that our approach achieves improved robustness under adversarial attacks compared to SFT models. Experiments on six meme classification datasets show that our approach achieves state-of-the-art performance, outperforming larger agentic systems. Moreover, our method generates higher-quality rationales for explaining hateful content compared to standard SFT, enhancing model interpretability. Code available at https://github.com/JingbiaoMei/RGCL
Authors: Teng Lin, Yuyu Luo, Nan Tang
Abstract: Multi-entity question answering (MEQA) represents significant challenges for large language models (LLM) and retrieval-augmented generation (RAG) systems, which frequently struggle to consolidate scattered information across diverse documents. While existing methods excel at single-document comprehension, they often struggle with cross-document aggregation, particularly when resolving entity-dense questions like "What is the distribution of ACM Fellows among various fields of study?", which require integrating entity-centric insights from heterogeneous sources (e.g., Wikipedia pages). To address this gap, we introduce MEBench, a novel multi-document, multi-entity benchmark designed to systematically evaluate LLMs' capacity to retrieve, consolidate, and reason over fragmented information. Our benchmark comprises 4,780 questions which are systematically categorized into three primary categories, further divided into eight distinct types, ensuring broad coverage of real-world multi-entity reasoning scenarios. Our experiments on state-of-the-art LLMs (e.g., GPT-4, Llama-3) and RAG pipelines reveal critical limitations: even advanced models achieve only 59% accuracy on MEBench. Our benchmark emphasizes the importance of completeness and factual precision of information extraction in MEQA tasks, using Entity-Attributed F1 (EA-F1) metric for granular evaluation of entity-level correctness and attribution validity. MEBench not only highlights systemic weaknesses in current LLM frameworks but also provides a foundation for advancing robust, entity-aware QA architectures.
Authors: Zhengdong Yang, Shuichiro Shimizu, Yahan Yu, Chenhui Chu
Abstract: Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which is naturally related to text. This paper surveys the integration of speech with LLMs, categorizing the methodologies into three primary approaches: text-based, latent-representation-based, and audio-token-based integration. We also demonstrate how these methods are applied across various speech-related applications and highlight the challenges in this field to offer inspiration for
Authors: Tom Kempton, Stuart Burrell
Abstract: Advances in hardware and language model architecture have spurred a revolution in natural language generation. However, autoregressive models compute probability distributions over next-token choices, and sampling from these distributions, known as decoding, has received significantly less attention than other design choices. Existing decoding strategies are largely based on heuristics, resulting in methods that are difficult to apply or improve in a principled manner. We develop the theory of decoding strategies for language models by expressing popular decoding algorithms as equilibrium states in the language of ergodic theory and stating the objective functions they optimize. Using this, we analyze the effect of the local normalization step required to make probabilities sum to one in top-k, nucleus, and temperature sampling. We argue that local normalization distortion is a fundamental defect of decoding strategies and quantify the size of this distortion and its effect on mathematical proxies for the quality and diversity of generated text. This yields conclusions for the design of decoding algorithms and the detection of machine-generated text.
Authors: Amanda Myntti, Erik Henriksson, Veronika Laippala, Sampo Pyysalo
Abstract: Pretraining data curation is a cornerstone in Large Language Model (LLM) development, leading to growing research on quality filtering of large web corpora. From statistical quality flags to LLM-based labelling systems, datasets are divided into categories, frequently reducing to a binary: those passing the filters are deemed as valuable examples, others are discarded as useless or detrimental. However, a more detailed understanding of the contribution of different kinds of texts to model performance is still largely lacking. In this article, we present the first study utilising registers or genres - a widely used standard in corpus linguistics to model linguistic variation - to curate pretraining datasets and investigate the effect of register on the performance of LLMs. We train small generative models with register classified data and evaluate them using standard benchmarks, and show that the register of pretraining data substantially affects model performance. We uncover surprising relationships between the pretraining material and the resulting models: using the News register results in subpar performance, and on the contrary, including the Opinion class, covering texts such as reviews and opinion blogs, is highly beneficial. While a model trained on the entire unfiltered dataset outperforms those trained on datasets limited to a single register, combining well-performing registers like How-to-Instructions, Informational Description, and Opinion leads to major improvements. Furthermore, analysis of individual benchmark results reveals key differences in the strengths and drawbacks of specific register classes as pretraining data. These findings show that register is an important explainer of model variation and can facilitate more deliberate future data selection practices.
Authors: Gautam Kishore Shahi, Oshani Seneviratne, Marc Spaniol
Abstract: With the shift from traditional to digital media, the online landscape now hosts not only reliable news articles but also a significant amount of unreliable content. Digital media has faster reachability by significantly influencing public opinion and advancing political agendas. While newspaper readers may be familiar with their preferred outlets political leanings or credibility, determining unreliable news articles is much more challenging. The credibility of many online sources is often opaque, with AI generated content being easily disseminated at minimal cost. Unreliable news articles, particularly those that followed the Russian invasion of Ukraine in 2022, closely mimic the topics and writing styles of credible sources, making them difficult to distinguish. To address this, we introduce SemCAFE, a system designed to detect news reliability by incorporating entity relatedness into its assessment. SemCAFE employs standard Natural Language Processing techniques, such as boilerplate removal and tokenization, alongside entity level semantic analysis using the YAGO knowledge base. By creating a semantic fingerprint for each news article, SemCAFE could assess the credibility of 46,020 reliable and 3,407 unreliable articles on the 2022 Russian invasion of Ukraine. Our approach improved the macro F1 score by 12% over state of the art methods. The sample data and code are available on GitHub
Authors: Hanhua Hong, Chenghao Xiao, Yang Wang, Yiqi Liu, Wenge Rong, Chenghua Lin
Abstract: Evaluating natural language generation systems is challenging due to the diversity of valid outputs. While human evaluation is the gold standard, it suffers from inconsistencies, lack of standardisation, and demographic biases, limiting reproducibility. LLM-based evaluators offer a scalable alternative but are highly sensitive to prompt design, where small variations can lead to significant discrepancies. In this work, we propose an inversion learning method that learns effective reverse mappings from model outputs back to their input instructions, enabling the automatic generation of highly effective, model-specific evaluation prompts. Our method requires only a single evaluation sample and eliminates the need for time-consuming manual prompt engineering, thereby improving both efficiency and robustness. Our work contributes toward a new direction for more robust and efficient LLM-based evaluation.
Authors: Akhiad Bercovich, Itay Levy, Izik Golan, Mohammad Dabbah, Ran El-Yaniv, Omri Puny, Ido Galil, Zach Moshe, Tomer Ronen, Najeeb Nabwani, Ido Shahaf, Oren Tropp, Ehud Karpas, Ran Zilberstein, Jiaqi Zeng, Soumye Singhal, Alexander Bukharin, Yian Zhang, Tugrul Konuk, Gerald Shen, Ameya Sunil Mahabaleshwarkar, Bilal Kartal, Yoshi Suhara, Olivier Delalleau, Zijia Chen, Zhilin Wang, David Mosallanezhad, Adi Renduchintala, Haifeng Qian, Dima Rekesh, Fei Jia, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad, Sean Narenthiran, Aleksander Ficek, Mehrzad Samadi, Jocelyn Huang, Siddhartha Jain, Igor Gitman, Ivan Moshkov, Wei Du, Shubham Toshniwal, George Armstrong, Branislav Kisacanin, Matvei Novikov, Daria Gitman, Evelina Bakhturina, Prasoon Varshney, Makesh Narsimhan, Jane Polak Scowcroft, John Kamalu, Dan Su, Kezhi Kong, Markus Kliegl, Rabeeh Karimi Mahabadi, Ying Lin, Sanjeev Satheesh, Jupinder Parmar, Pritam Gundecha, Brandon Norick, Joseph Jennings, Shrimai Prabhumoye, Syeda Nahida Akter, Mostofa Patwary, Abhinav Khattar, Deepak Narayanan, Roger Waleffe, Jimmy Zhang, Bor-Yiing Su, Guyue Huang, Terry Kong, Parth Chadha, Sahil Jain, Christine Harvey, Elad Segal, Jining Huang, Sergey Kashirsky, Robert McQueen, Izzy Putterman, George Lam, Arun Venkatesan, Sherry Wu, Vinh Nguyen, Manoj Kilaru, Andrew Wang, Anna Warno, Abhilash Somasamudramath, Sandip Bhaskar, Maka Dong, Nave Assaf, Shahar Mor, Omer Ullman Argov, Scot Junkin, Oleksandr Romanenko, Pedro Larroy, Monika Katariya, Marco Rovinelli, Viji Balas, Nicholas Edelman, Anahita Bhiwandiwalla, Muthu Subramaniam, Smita Ithape, Karthik Ramamoorthy, Yuting Wu, Suguna Varshini Velury, Omri Almog, Joyjit Daw, Denys Fridman, Erick Galinkin, Michael Evans, Shaona Ghosh, Katherine Luna, Leon Derczynski, Nikki Pope, Eileen Long, Seth Schneider, Guillermo Siman, Tomasz Grzegorzek, Pablo Ribalta, Monika Katariya, Chris Alexiuk, Joey Conway, Trisha Saar, Ann Guan, Krzysztof Pawelec, Shyamala Prayaga, Oleksii Kuchaiev, Boris Ginsburg, Oluwatobi Olabiyi, Kari Briski, Jonathan Cohen, Bryan Catanzaro, Jonah Alben, Yonatan Geifman, Eric Chung
Abstract: We introduce the Llama-Nemotron series of models, an open family of heterogeneous reasoning models that deliver exceptional reasoning capabilities, inference efficiency, and an open license for enterprise use. The family comes in three sizes -- Nano (8B), Super (49B), and Ultra (253B) -- and performs competitively with state-of-the-art reasoning models such as DeepSeek-R1 while offering superior inference throughput and memory efficiency. In this report, we discuss the training procedure for these models, which entails using neural architecture search from Llama 3 models for accelerated inference, knowledge distillation, and continued pretraining, followed by a reasoning-focused post-training stage consisting of two main parts: supervised fine-tuning and large scale reinforcement learning. Llama-Nemotron models are the first open-source models to support a dynamic reasoning toggle, allowing users to switch between standard chat and reasoning modes during inference. To further support open research and facilitate model development, we provide the following resources: 1. We release the Llama-Nemotron reasoning models -- LN-Nano, LN-Super, and LN-Ultra -- under the commercially permissive NVIDIA Open Model License Agreement. 2. We release the complete post-training dataset: Llama-Nemotron-Post-Training-Dataset. 3. We also release our training codebases: NeMo, NeMo-Aligner, and Megatron-LM.
Authors: Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu
Abstract: Large language models (LLMs) trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose \textbf{OBLIVIATE}, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extracting target tokens, building retain sets, and fine-tuning with a tailored loss function comprising three components -- masking, distillation, and world fact. Using low-rank adapters (LoRA) ensures efficiency without compromising unlearning quality. We conduct experiments on multiple datasets, including Harry Potter series, WMDP, and TOFU, using a comprehensive suite of metrics: \emph{forget quality} (via a new document-level memorization score), \emph{model utility}, and \emph{fluency}. Results demonstrate its effectiveness in resisting membership inference attacks, minimizing the impact on retained data, and maintaining robustness across diverse scenarios.
Authors: Haoming Huang, Yibo Yan, Jiahao Huo, Xin Zou, Xinfeng Li, Kun Wang, Xuming Hu
Abstract: Large Language Models (LLMs), despite their remarkable capabilities, are hampered by hallucinations. A particularly challenging variant, knowledge overshadowing, occurs when one piece of activated knowledge inadvertently masks another relevant piece, leading to erroneous outputs even with high-quality training data. Current understanding of overshadowing is largely confined to inference-time observations, lacking deep insights into its origins and internal mechanisms during model training. Therefore, we introduce PhantomCircuit, a novel framework designed to comprehensively analyze and detect knowledge overshadowing. By innovatively employing knowledge circuit analysis, PhantomCircuit dissects the function of key components in the circuit and how the attention pattern dynamics contribute to the overshadowing phenomenon and its evolution throughout the training process. Extensive experiments demonstrate PhantomCircuit's effectiveness in identifying such instances, offering novel insights into this elusive hallucination and providing the research community with a new methodological lens for its potential mitigation.
Authors: Shinnosuke Ono, Issey Sukeda, Takuro Fujii, Kosei Buma, Shunsuke Sasaki
Abstract: We present a Japanese domain-specific language model for the pharmaceutical field, developed through continual pretraining on 2 billion Japanese pharmaceutical tokens and 8 billion English biomedical tokens. To enable rigorous evaluation, we introduce three new benchmarks: YakugakuQA, based on national pharmacist licensing exams; NayoseQA, which tests cross-lingual synonym and terminology normalization; and SogoCheck, a novel task designed to assess consistency reasoning between paired statements. We evaluate our model against both open-source medical LLMs and commercial models, including GPT-4o. Results show that our domain-specific model outperforms existing open models and achieves competitive performance with commercial ones, particularly on terminology-heavy and knowledge-based tasks. Interestingly, even GPT-4o performs poorly on SogoCheck, suggesting that cross-sentence consistency reasoning remains an open challenge. Our benchmark suite offers a broader diagnostic lens for pharmaceutical NLP, covering factual recall, lexical variation, and logical consistency. This work demonstrates the feasibility of building practical, secure, and cost-effective language models for Japanese domain-specific applications, and provides reusable evaluation resources for future research in pharmaceutical and healthcare NLP. Our model, codes, and datasets are released at https://github.com/EQUES-Inc/pharma-LLM-eval.
Authors: Suifeng Zhao, Zhuoran Jin, Sujian Li, Jun Gao
Abstract: Retrieval-Augmented Generation (RAG) plays a vital role in the financial domain, powering applications such as real-time market analysis, trend forecasting, and interest rate computation. However, most existing RAG research in finance focuses predominantly on textual data, overlooking the rich visual content in financial documents, resulting in the loss of key analytical insights. To bridge this gap, we present FinRAGBench-V, a comprehensive visual RAG benchmark tailored for finance which effectively integrates multimodal data and provides visual citation to ensure traceability. It includes a bilingual retrieval corpus with 60,780 Chinese and 51,219 English pages, along with a high-quality, human-annotated question-answering (QA) dataset spanning heterogeneous data types and seven question categories. Moreover, we introduce RGenCite, an RAG baseline that seamlessly integrates visual citation with generation. Furthermore, we propose an automatic citation evaluation method to systematically assess the visual citation capabilities of Multimodal Large Language Models (MLLMs). Extensive experiments on RGenCite underscore the challenging nature of FinRAGBench-V, providing valuable insights for the development of multimodal RAG systems in finance.
Authors: Tao Liu, Xutao Mao, Hongying Zan, Dixuan Zhang, Yifan Li, Haixin Liu, Lulu Kong, Jiaming Hou, Rui Li, YunLong Li, aoze zheng, Zhiqiang Zhang, Luo Zhewei, Kunli Zhang, Min Peng
Abstract: Text-to-SQL is a critical task in natural language processing that aims to transform natural language questions into accurate and executable SQL queries. In real-world scenarios, these reasoning tasks are often accompanied by complex mathematical computations, domain knowledge, and hypothetical reasoning scenarios. However, existing large-scale Text-to-SQL datasets typically focus on business logic and task logic, neglecting critical factors such as vertical domain knowledge, complex mathematical reasoning, and hypothetical reasoning, which are essential for realistically reflecting the reasoning demands in practical applications and completing data querying and analysis. To bridge this gap, we introduce LogicCat, the first Text-to-SQL benchmark dataset specifically designed for complex reasoning and chain-of-thought parsing, encompassing physics, arithmetic, commonsense, and hypothetical reasoning scenarios. LogicCat comprises 4,038 English questions paired 12,114 detailed chain-of-thought reasoning steps, spanning 45 databases across diverse domains, significantly surpassing existing datasets in complexity. Experimental results demonstrate that LogicCat substantially increases the task difficulty for current state-of-the-art models to at most 33.20% execution accuracy, indicating that this task remains exceptionally challenging. The advancement of LogicCat represents a crucial step toward developing systems suitable for real-world enterprise data analysis and autonomous query generation. We have released our dataset code at https://github.com/Ffunkytao/LogicCat.
Authors: Chengyan Wu, Yiqiang Cai, Yang Liu, Pengxu Zhu, Yun Xue, Ziwei Gong, Julia Hirschberg, Bolei Ma
Abstract: While text-based emotion recognition methods have achieved notable success, real-world dialogue systems often demand a more nuanced emotional understanding than any single modality can offer. Multimodal Emotion Recognition in Conversations (MERC) has thus emerged as a crucial direction for enhancing the naturalness and emotional understanding of human-computer interaction. Its goal is to accurately recognize emotions by integrating information from various modalities such as text, speech, and visual signals. This survey offers a systematic overview of MERC, including its motivations, core tasks, representative methods, and evaluation strategies. We further examine recent trends, highlight key challenges, and outline future directions. As interest in emotionally intelligent systems grows, this survey provides timely guidance for advancing MERC research.
Authors: Celia Cintas, Miriam Rateike, Erik Miehling, Elizabeth Daly, Skyler Speakman
Abstract: We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the representation space of large language models (LLMs). Using a range of dimension reduction and pattern recognition methods, we first identify the model layers that show the greatest divergence in encoding these representations. We then analyze the activations within a selected layer to examine how specific personas are encoded relative to others, including their shared and distinct embedding spaces. We find that, across multiple pre-trained decoder-only LLMs, the analyzed personas show large differences in representation space only within the final third of the decoder layers. We observe overlapping activations for specific ethical perspectives -- such as moral nihilism and utilitarianism -- suggesting a degree of polysemy. In contrast, political ideologies like conservatism and liberalism appear to be represented in more distinct regions. These findings help to improve our understanding of how LLMs internally represent information and can inform future efforts in refining the modulation of specific human traits in LLM outputs. Warning: This paper includes potentially offensive sample statements.
Authors: Manon Reusens, Bart Baesens, David Jurgens
Abstract: Personalized Large Language Models (LLMs) are increasingly used in diverse applications, where they are assigned a specific persona - such as a happy high school teacher - to guide their responses. While prior research has examined how well LLMs adhere to predefined personas in writing style, a comprehensive analysis of consistency across different personas and task types is lacking. In this paper, we introduce a new standardized framework to analyze consistency in persona-assigned LLMs. We define consistency as the extent to which a model maintains coherent responses when assigned the same persona across different tasks and runs. Our framework evaluates personas across four different categories (happiness, occupation, personality, and political stance) spanning multiple task dimensions (survey writing, essay generation, social media post generation, single turn, and multi-turn conversations). Our findings reveal that consistency is influenced by multiple factors, including the assigned persona, stereotypes, and model design choices. Consistency also varies across tasks, increasing with more structured tasks and additional context. All code is available on GitHub.
Authors: Noy Sternlicht, Ariel Gera, Roy Bar-Haim, Tom Hope, Noam Slonim
Abstract: We introduce Debate Speech Evaluation as a novel and challenging benchmark for assessing LLM judges. Evaluating debate speeches requires a deep understanding of the speech at multiple levels, including argument strength and relevance, the coherence and organization of the speech, the appropriateness of its style and tone, and so on. This task involves a unique set of cognitive abilities that previously received limited attention in systematic LLM benchmarking. To explore such skills, we leverage a dataset of over 600 meticulously annotated debate speeches and present the first in-depth analysis of how state-of-the-art LLMs compare to human judges on this task. Our findings reveal a nuanced picture: while larger models can approximate individual human judgments in some respects, they differ substantially in their overall judgment behavior. We also investigate the ability of frontier LLMs to generate persuasive, opinionated speeches, showing that models may perform at a human level on this task.
Authors: Yuan Chang, Ziyue Li, Hengyuan Zhang, Yuanbo Kong, Yanru Wu, Hayden Kwok-Hay So, Zhijiang Guo, Liya Zhu, Ngai Wong
Abstract: While Large Language Models (LLMs) have shown significant potential in assisting peer review, current methods often struggle to generate thorough and insightful reviews while maintaining efficiency. In this paper, we propose TreeReview, a novel framework that models paper review as a hierarchical and bidirectional question-answering process. TreeReview first constructs a tree of review questions by recursively decomposing high-level questions into fine-grained sub-questions and then resolves the question tree by iteratively aggregating answers from leaf to root to get the final review. Crucially, we incorporate a dynamic question expansion mechanism to enable deeper probing by generating follow-up questions when needed. We construct a benchmark derived from ICLR and NeurIPS venues to evaluate our method on full review generation and actionable feedback comments generation tasks. Experimental results of both LLM-based and human evaluation show that TreeReview outperforms strong baselines in providing comprehensive, in-depth, and expert-aligned review feedback, while reducing LLM token usage by up to 80% compared to computationally intensive approaches. Our code and benchmark dataset are available at https://github.com/YuanChang98/tree-review.
Authors: Ke Wang, Yiming Qin, Nikolaos Dimitriadis, Alessandro Favero, Pascal Frossard
Abstract: Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, editing such models efficiently and reliably-without retraining or forgetting previous information-remains a major challenge. Existing methods for lifelong model editing either compromise generalization, interfere with past edits, or fail to scale to long editing sequences. We propose MEMOIR, a novel scalable framework that injects knowledge through a residual memory, i.e., a dedicated parameter module, while preserving the core capabilities of the pre-trained model. By sparsifying input activations through sample-dependent masks, MEMOIR confines each edit to a distinct subset of the memory parameters, minimizing interference among edits. At inference, it identifies relevant edits by comparing the sparse activation patterns of new queries to those stored during editing. This enables generalization to rephrased queries by activating only the relevant knowledge while suppressing unnecessary memory activation for unrelated prompts. Experiments on question answering, hallucination correction, and out-of-distribution generalization benchmarks for LLaMA-3 and Mistral backbones demonstrate that MEMOIR achieves state-of-the-art performance across reliability, generalization, and locality metrics, scaling to thousands of sequential edits with minimal forgetting.
Authors: Nathaniel Getachew, Abulhair Saparov
Abstract: We introduce $\texttt{StorySim}$, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling (WM) capabilities of large language models (LLMs). Unlike prior benchmarks that may suffer from contamination in pretraining data, $\texttt{StorySim}$ produces novel, compositional story prompts anchored by a highly controllable $\texttt{Storyboard}$, enabling precise manipulation of character perspectives and events. We use this framework to design first- and second-order ToM tasks alongside WM tasks that control for the ability to track and model mental states. Our experiments across a suite of state-of-the-art LLMs reveal that most models perform better on WM tasks than ToM tasks, and that models tend to perform better reasoning with humans compared to inanimate objects. Additionally, our framework enabled us to find evidence of heuristic behavior such as recency bias and an over-reliance on earlier events in the story. All code for generating data and evaluations is freely available.
Authors: Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, Jingbo Zhu
Abstract: Test-Time Scaling (TTS) is a promising approach to progressively elicit the model's intelligence during inference. Recently, training-based TTS methods, such as continued reinforcement learning (RL), have further surged in popularity, while training-free TTS methods are gradually fading from prominence. However, the additional computation overhead of training amplifies the burden on test-time scaling. In this paper, we focus on training-free TTS methods for reasoning. We first design Conditional Step-level Self-refinement, a fine-grained sequential scaling method guided by process verification. On top of its effectiveness, we further combine it with other classical parallel scaling methods at the step level, to introduce a novel inference paradigm called Hybrid Test-Time Scaling. Extensive experiments on five instruction-tuned LLMs across different scales (3B-14B) and families demonstrate that hybrid strategy incorporating various training-free TTS methods at a fine granularity has considerable potential for expanding the reasoning performance boundaries of LLMs.
Authors: Supantho Rakshit, Adele Goldberg
Abstract: The usage-based constructionist (UCx) approach to language posits that language comprises a network of learned form-meaning pairings (constructions) whose use is largely determined by their meanings or functions, requiring them to be graded and probabilistic. This study investigates whether the internal representations in Large Language Models (LLMs) reflect the proposed function-infused gradience. We analyze representations of the English Double Object (DO) and Prepositional Object (PO) constructions in Pythia-$1.4$B, using a dataset of $5000$ sentence pairs systematically varied by human-rated preference strength for DO or PO. Geometric analyses show that the separability between the two constructions' representations, as measured by energy distance or Jensen-Shannon divergence, is systematically modulated by gradient preference strength, which depends on lexical and functional properties of sentences. That is, more prototypical exemplars of each construction occupy more distinct regions in activation space, compared to sentences that could have equally well have occured in either construction. These results provide evidence that LLMs learn rich, meaning-infused, graded representations of constructions and offer support for geometric measures for representations in LLMs.
Authors: Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner, Peter Viechnicki, Najim Dehak
Abstract: In dialogue transcription pipelines, Large Language Models (LLMs) are frequently employed in post-processing to improve grammar, punctuation, and readability. We explore a complementary post-processing step: enriching transcribed dialogues by adding metadata tags for speaker characteristics such as age, gender, and emotion. Some of the tags are global to the entire dialogue, while some are time-variant. Our approach couples frozen audio foundation models, such as Whisper or WavLM, with a frozen LLAMA language model to infer these speaker attributes, without requiring task-specific fine-tuning of either model. Using lightweight, efficient connectors to bridge audio and language representations, we achieve competitive performance on speaker profiling tasks while preserving modularity and speed. Additionally, we demonstrate that a frozen LLAMA model can compare x-vectors directly, achieving an Equal Error Rate of 8.8% in some scenarios.
Authors: Samyak S. Sanghvi
Abstract: Antonym vs synonym distinction across multiple languages presents unique computational challenges due to the paradoxical nature of antonymous relationships words that share semantic domains while expressing opposite meanings. This work introduces Bhav-Net, a novel dual-space architecture that enables effective knowledge transfer from complex multilingual models to simpler, language-specific architectures while maintaining robust cross-lingual antonym--synonym distinction capabilities. Our approach combines language-specific BERT encoders with graph transformer networks, creating distinct semantic projections where synonymous pairs cluster in one space while antonymous pairs exhibit high similarity in a complementary space. Through comprehensive evaluation across eight languages (English, German, French, Spanish, Italian, Portuguese, Dutch, and Russian), we demonstrate that semantic relationship modeling transfers effectively across languages. The dual-encoder design achieves competitive performance against state-of-the-art baselines while providing interpretable semantic representations and effective cross-lingual generalization.
Authors: V Venktesh, Mandeep Rathee, Avishek Anand
Abstract: Test-time scaling (TTS) has emerged as a new frontier for scaling the performance of Large Language Models. In test-time scaling, by using more computational resources during inference, LLMs can improve their reasoning process and task performance. Several approaches have emerged for TTS such as distilling reasoning traces from another model or exploring the vast decoding search space by employing a verifier. The verifiers serve as reward models that help score the candidate outputs from the decoding process to diligently explore the vast solution space and select the best outcome. This paradigm commonly termed has emerged as a superior approach owing to parameter free scaling at inference time and high performance gains. The verifiers could be prompt-based, fine-tuned as a discriminative or generative model to verify process paths, outcomes or both. Despite their widespread adoption, there is no detailed collection, clear categorization and discussion of diverse verification approaches and their training mechanisms. In this survey, we cover the diverse approaches in the literature and present a unified view of verifier training, types and their utility in test-time scaling. Our repository can be found at https://github.com/elixir-research-group/Verifierstesttimescaling.github.io.
URLs: https://github.com/elixir-research-group/Verifierstesttimescaling.github.io.
Authors: Bryan Chen Zhengyu Tan, Daniel Wai Kit Chin, Zhengyuan Liu, Nancy F. Chen, Roy Ka-Wei Lee
Abstract: Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues, a critical challenge for reliable deployment. We introduce DuET-PD (Dual Evaluation for Trust in Persuasive Dialogues), a framework evaluating multi-turn stance-change dynamics across dual dimensions: persuasion type (corrective/misleading) and domain (knowledge via MMLU-Pro, and safety via SALAD-Bench). We find that even a state-of-the-art model like GPT-4o achieves only 27.32% accuracy in MMLU-Pro under sustained misleading persuasions. Moreover, results reveal a concerning trend of increasing sycophancy in newer open-source models. To address this, we introduce Holistic DPO, a training approach balancing positive and negative persuasion examples. Unlike prompting or resist-only training, Holistic DPO enhances both robustness to misinformation and receptiveness to corrections, improving Llama-3.1-8B-Instruct's accuracy under misleading persuasion in safety contexts from 4.21% to 76.54%. These contributions offer a pathway to developing more reliable and adaptable LLMs for multi-turn dialogue. Code is available at https://github.com/Social-AI-Studio/DuET-PD.
Authors: Lang Xiong, Nishant Bhargava, Jeremy Chang, Jianhang Hong, Haihao Liu, Vasu Sharma, Kevin Zhu
Abstract: Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy poses a critical challenge for AI alignment, as benchmark performance may not accurately reflect a model's true safety and honesty. In this work, we systematically quantify these behavioral changes by manipulating the perceived context of prompts. We introduce a methodology that uses a linear probe to score prompts on a continuous scale from "test-like" to "deploy-like" and leverage an LLM rewriting strategy to shift these prompts towards a more natural, deployment-style context while preserving the original task. Using this method, we achieved a 30% increase in the average probe score across a strategic role-playing dataset after rewriting. Evaluating a suite of state-of-the-art models on these original and rewritten prompts, we find that rewritten "deploy-like" prompts induce a significant and consistent shift in behavior. Across all models, we observed an average increase in honest responses of 5.26% and a corresponding average decrease in deceptive responses of 12.40%. Furthermore, refusal rates increased by an average of 6.38%, indicating heightened safety compliance. Our findings demonstrate that evaluation awareness is a quantifiable and manipulable factor that directly influences LLM behavior, revealing that models are more prone to unsafe or deceptive outputs in perceived test environments. This underscores the urgent need for more realistic evaluation frameworks to accurately gauge true model alignment before deployment.
Authors: Xuemei Tang, Chengxi Yan, Jinghang Gu, Chu-Ren Huang
Abstract: Chinese information extraction (IE) involves multiple tasks across diverse temporal domains, including Classical and Modern documents. Fine-tuning a single model on heterogeneous tasks and across different eras may lead to interference and reduced performance. Therefore, in this paper, we propose Tea-MOELoRA, a parameter-efficient multi-task framework that combines LoRA with a Mixture-of-Experts (MoE) design. Multiple low-rank LoRA experts specialize in different IE tasks and eras, while a task-era-aware router mechanism dynamically allocates expert contributions. Experiments show that Tea-MOELoRA outperforms both single-task and joint LoRA baselines, demonstrating its ability to leverage task and temporal knowledge effectively.
Authors: Kairong Han, Wenshuo Zhao, Ziyu Zhao, JunJian Ye, Lujia Pan, Kun Kuang
Abstract: Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture spurious correlations rather than true causal relationships, leading to suboptimal performance, especially in out-of-distribution (OOD) scenarios. To address this challenge, we propose Causal Attention Tuning (CAT), a novel approach that injects fine-grained causal knowledge into the attention mechanism. We propose an automated pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training, helping the model focus on causal structures while mitigating noise and biases in attention scores. Experimental results on our proposed Spurious Token Game (STG) benchmark and multiple downstream tasks demonstrate that our approach effectively leverages causal knowledge for prediction and remains robust in OOD scenarios. The CAT achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks. Notably, the OOD performance of the Llama-3.1-8B model on STG_M increased from 64.5% to 90.5%, and Qwen's OOD performance on the STG_H dataset improved from 25.4% to 55.9%. Implementation details can be found at https://github.com/Kairong-Han/CAT.
Authors: Chang Su, Dengliang Shi, Siyuan Huang, Jintao Du, Changhua Meng, Yu Cheng, Weiqiang Wang, Zhouhan Lin
Abstract: Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final token, typically a reserved special token such as [EOS]. However, these tokens have not been intentionally trained to capture the semantics of the whole context, limiting their capacity as text embeddings, especially for retrieval and re-ranking tasks. We propose to add a new training stage before contrastive learning to enrich the semantics of the final token embedding. This stage employs bidirectional generative reconstruction tasks, namely EBQ2D (Embedding-Based Query-to-Document) and EBD2Q (Embedding-Based Document-to-Query), which interleave to anchor the [EOS] embedding and reconstruct either side of Query-Document pairs. Experimental results demonstrate that our additional training stage significantly improves LLM performance on the Massive Text Embedding Benchmark (MTEB), achieving new state-of-the-art results across different LLM base models and scales.
Authors: Bufan Gao, Elisa Kreiss
Abstract: As LLMs are increasingly applied in socially impactful settings, concerns about gender bias have prompted growing efforts both to measure and mitigate such bias. These efforts often rely on evaluation tasks that differ from natural language distributions, as they typically involve carefully constructed task prompts that overtly or covertly signal the presence of gender bias-related content. In this paper, we examine how signaling the evaluative purpose of a task impacts measured gender bias in LLMs. Concretely, we test models under prompt conditions that (1) make the testing context salient, and (2) make gender-focused content salient. We then assess prompt sensitivity across four task formats with both token-probability and discrete-choice metrics. We find that prompts that more clearly align with (gender bias) evaluation framing elicit distinct gender output distributions compared to less evaluation-framed prompts. Discrete-choice metrics further tend to amplify bias relative to probabilistic measures. These findings do not only highlight the brittleness of LLM gender bias evaluations but open a new puzzle for the NLP benchmarking and development community: To what extent can well-controlled testing designs trigger LLM "testing mode" performance, and what does this mean for the ecological validity of future benchmarks.
Authors: Dhruvi Paprunia, Vansh Kharidia, Pankti Doshi
Abstract: In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use tools effectively has become a defining feature of Large Language Models (LLMs), allowing them to access external data and internal resources. As AI agents grow more sophisticated, tool-use capabilities have become indispensable. While LLMs have made significant progress in this area, Small Language Models (SLMs) still face challenges in accurately integrating tool use, especially in resource-constrained settings. This study investigates how Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), can enhance the tool-use accuracy of SLMs. By designing a well-defined reward system that reinforces structured JSON output, correct tool selection, and precise parameter usage, we demonstrate that GRPO enables SLMs to achieve significant improvements in tool-use capabilities (function calling/JSON output). Our approach provides a computationally efficient training method that enhances SLMs practical deployment in real-world AI applications.
Authors: Aisha Alansari, Hamzah Luqman
Abstract: Recently, extensive research on the hallucination of the large language models (LLMs) has mainly focused on the English language. Despite the growing number of multilingual and Arabic-specific LLMs, evaluating LLMs' hallucination in the Arabic context remains relatively underexplored. The knowledge gap is particularly pressing given Arabic's widespread use across many regions and its importance in global communication and media. This paper presents the first comprehensive hallucination evaluation of Arabic and multilingual LLMs on two critical Arabic natural language generation tasks: generative question answering (GQA) and summarization. This study evaluates a total of 12 LLMs, including 4 Arabic pre-trained models, 4 multilingual models, and 4 reasoning-based models. To assess the factual consistency and faithfulness of LLMs' outputs, we developed a fine-grained hallucination evaluation framework consisting of 12 fine-grained hallucination indicators that represent the varying characteristics of each task. The results reveal that factual hallucinations are more prevalent than faithfulness errors across all models and tasks. Notably, the Arabic pre-trained model Allam consistently demonstrates lower hallucination rates than multilingual models and a comparative performance with reasoning-based models. The code is available at: https://github.com/aishaalansari57/AraHalluEval
Authors: Mao Zheng, Zheng Li, Bingxin Qu, Mingyang Song, Yang Du, Mingrui Sun, Di Wang
Abstract: In this report, we introduce Hunyuan-MT-7B, our first open-source multilingual translation model, which supports bidirectional translation across 33 major languages and places a special emphasis on translation between Mandarin and several ethnic minority languages as well as dialects. Furthermore, to serve and address diverse translation scenarios and enhance model performance at test time, we introduce Hunyuan-MT-Chimera-7B, a translation model inspired by the slow thinking mode. This model integrates multiple outputs generated by the Hunyuan-MT-7B model under varying parameter settings, thereby achieving performance superior to that of conventional slow-thinking models based on Chain-of-Thought (CoT). The development of our models follows a holistic training process specifically engineered for multilingual translation, which begins with general and MT-oriented pre-training to build foundational capabilities, proceeds to Supervised Fine-Tuning (SFT) for task-specific adaptation, and culminates in advanced alignment through Reinforcement Learning (RL) and weak-to-strong RL. Through comprehensive experimentation, we demonstrate that both Hunyuan-MT-7B and Hunyuan-MT-Chimera-7B significantly outperform all translation-specific models of comparable parameter size and most of the SOTA large models, particularly on the task of translation between Mandarin and minority languages as well as dialects. In the WMT2025 shared task (General Machine Translation), our models demonstrate state-of-the-art performance, ranking first in 30 out of 31 language pairs. This result highlights the robustness of our models across a diverse linguistic spectrum, encompassing high-resource languages such as Chinese, English, and Japanese, as well as low-resource languages including Czech, Marathi, Estonian, and Icelandic.
Authors: Hongyan Xie, Yitong Yao, Yikun Ban, Zixuan Huang, Deqing Wang, Zhenhe Wu, Haoxiang Su, Chao Wang, Shuangyong Song
Abstract: Large language models (LLMs) excel at reasoning tasks but are expensive to deploy. Thus small language models (SLMs) are fine-tuned on CoT data generated by LLMs to copy LLMs' abilities. However, these CoT data may include noisy rationales that either fail to substantiate the answers or contribute no additional information to support answer prediction, which leads SLMs to capture spurious correlations between questions and answers and compromise the quality of reasoning. In this work, we propose Chain-of-Thought Correctness Perception Distillation (CoPeD), which aims to improve the reasoning quality of the student model from the perspectives of task setting and data utilization. Firstly, we introduce a correctness-aware task setting that encourages the student model to predict answers based on correct rationales and revise them when they are incorrect. This setting improves the faithfulness of reasoning and allows the model to learn from its mistakes. Then, we propose a Correctness-Aware Weighted loss, which dynamically adjusts the contribution of each training instance based on the combined loss of the rationale and the answer. This strategy encourages the model to focus more on samples where the rationale offers stronger support for the correct answer. Experiments have shown that CoPeD is effective on both in-distribution (IND) and out-of-distribution (OOD) benchmark reasoning datasets.
Authors: Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zhen, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li
Abstract: Recent progress in Large Language Models (LLMs) has opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). However, existing LLM-driven NAS approaches rely heavily on prompt engineering and domain-specific tuning, limiting their practicality and scalability across diverse tasks. In this work, we propose LM-Searcher, a novel framework that leverages LLMs for cross-domain neural architecture optimization without the need for extensive domain-specific adaptation. Central to our approach is NCode, a universal numerical string representation for neural architectures, which enables cross-domain architecture encoding and search. We also reformulate the NAS problem as a ranking task, training LLMs to select high-performing architectures from candidate pools using instruction-tuning samples derived from a novel pruning-based subspace sampling strategy. Our curated dataset, encompassing a wide range of architecture-performance pairs, encourages robust and transferable learning. Comprehensive experiments demonstrate that LM-Searcher achieves competitive performance in both in-domain (e.g., CNNs for image classification) and out-of-domain (e.g., LoRA configurations for segmentation and generation) tasks, establishing a new paradigm for flexible and generalizable LLM-based architecture search. The datasets and models will be released at https://github.com/Ashone3/LM-Searcher.
Authors: Yi Xing
Abstract: Intertextuality is a central tenet in literary studies. It refers to the intricate links between literary texts that are created by various types of references. This paper proposes a new quantitative model of intertextuality to enable scalable analysis and network-based insights: perform pairwise comparisons of the embeddings of n-grams from two texts and average their results as the overall intertextuality. Validation on four texts with known degrees of intertextuality, alongside a scalability test on 267 diverse texts, demonstrates the method's effectiveness and efficiency. Network analysis further reveals centrality and community structures, affirming the approach's success in capturing and quantifying intertextual relationships.
Authors: Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu
Abstract: Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training strategies, ultimately enhancing their reasoning capability. In this study, we constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning. We introduced the concept of buffer mechanism: the model stores various information in distinct buffers and selectively extracts it through the query-key matrix. We proposed a random matrix-based algorithm to enhance the model's reasoning ability. This algorithm introduces only 132 trainable parameters, yet leads to significant performance improvements on 7 multi-step reasoning datasets, including PrOntoQA, LogicAsker, and LogicInference. These findings provide new insights into understanding the large language models.
Authors: Junjie Wang, Yuxiang Zhang, Minghao Liu, Yin Zhang, Yatai Ji, Weihao Xuan, Nie Lin, Kang Zhu, Zhiqiang Lin, Yiming Ren, Chunyang Jiang, Yiyao Yu, Zekun Wang, Tiezhen Wang, Wenhao Huang, Jie Fu, Qunshu Lin, Yujiu Yang, Ge Zhang, Ruibin Yuan, Bei Chen, Wenhu Chen
Abstract: Recent advancements in large multimodal models (LMMs) have leveraged extensive multimodal datasets to enhance capabilities in complex knowledge-driven tasks. However, persistent challenges in perceptual and reasoning errors limit their efficacy, particularly in interpreting intricate visual data and deducing multimodal relationships. To address these issues, we introduce PIN (Paired and INterleaved multimodal documents), a novel data format designed to foster a deeper integration of visual and textual knowledge. The PIN format uniquely combines semantically rich Markdown files, which preserve fine-grained textual structures, with holistic overall images that capture the complete document layout. Following this format, we construct and release two large-scale, open-source datasets: PIN-200M (~200 million documents) and PIN-14M (~14 million), compiled from diverse web and scientific sources in both English and Chinese. To maximize usability, we provide detailed statistical analyses and equip the datasets with quality signals, enabling researchers to easily filter and select data for specific tasks. Our work provides the community with a versatile data format and substantial resources, offering a foundation for new research in pre-training strategies and the development of more powerful knowledge-intensive LMMs.
Authors: Xintong Li, Junda Wu, Tong Yu, Yu Wang, Xiang Chen, Jiuxiang Gu, Lina Yao, Julian McAuley, Jingbo Shang
Abstract: Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy between the two modules so that LLMs can adapt their reasoning abilities to downstream tasks while feature encoders can adjust to provide more task-specific information about its modality. In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives, where we find the unbalanced learning between the feature encoder and the LLM can cause problems of oscillation and biased learning that lead to sub-optimal convergence. Inspired by our findings, we propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning. Based on this, we further design a dynamic learning scheduler that better coordinates the learning between the LLM and feature encoder, alleviating the problems of oscillation and biased learning. In addition, we introduce an auxiliary regularization on the gradient to promote updating with larger step sizes, which potentially allows for a more accurate estimation of the proposed MultiModal Balance Coefficient and further improves the training sufficiency. Our proposed approach is agnostic to the architecture of LLM and feature encoder, so it can be generically integrated with various MLLMs. We conduct experiments on multiple downstream tasks with various MLLMs, demonstrating that the proposed method is more effective than the baselines in MLLM instruction tuning.
Authors: Ada-Astrid Balauca, Sanjana Garai, Stefan Balauca, Rasesh Udayakumar Shetty, Naitik Agrawal, Dhwanil Subhashbhai Shah, Yuqian Fu, Xi Wang, Kristina Toutanova, Danda Pani Paudel, Luc Van Gool
Abstract: Museums serve as repositories of cultural heritage and historical artifacts from diverse epochs, civilizations, and regions, preserving well-documented collections that encapsulate vast knowledge, which, when systematically structured into large-scale datasets, can train specialized models. Visitors engage with exhibits through curiosity and questions, making expert domain-specific models essential for interactive query resolution and gaining historical insights. Understanding exhibits from images requires analyzing visual features and linking them to historical knowledge to derive meaningful correlations. We facilitate such reasoning by (a) collecting and curating a large-scale dataset of 65M images and 200M question-answer pairs for exhibits from all around the world; (b) training large vision-language models (VLMs) on the collected dataset; (c) benchmarking their ability on five visual question answering tasks, specifically designed to reflect real-world inquiries and challenges observed in museum settings. The complete dataset is labeled by museum experts, ensuring the quality and the practical significance of the labels. We train two VLMs from different categories: BLIP with vision-language aligned embeddings, but lacking the expressive power of large language models, and the LLaVA model, a powerful instruction-tuned LLM enriched with vision-language reasoning capabilities. Through extensive experiments, we find that while both model types effectively answer visually grounded questions, large vision-language models excel in queries requiring deeper historical context and reasoning. We further demonstrate the necessity of fine-tuning models on large-scale domain-specific datasets by showing that our fine-tuned models significantly outperform current SOTA VLMs in answering questions related to specific attributes, highlighting their limitations in handling complex, nuanced queries.
Authors: Nobin Sarwar
Abstract: Visual Question Answering requires models to generate accurate answers by integrating visual and textual understanding. However, VQA models still struggle with hallucinations, producing convincing but incorrect answers, particularly in knowledge-driven and Out-of-Distribution scenarios. We introduce FilterRAG, a retrieval-augmented framework that combines BLIP-VQA with Retrieval-Augmented Generation to ground answers in external knowledge sources like Wikipedia and DBpedia. FilterRAG achieves 36.5% accuracy on the OK-VQA dataset, demonstrating its effectiveness in reducing hallucinations and improving robustness in both in-domain and Out-of-Distribution settings. These findings highlight the potential of FilterRAG to improve Visual Question Answering systems for real-world deployment.
Authors: Tharindu Kumarage, Cameron Johnson, Jadie Adams, Lin Ai, Matthias Kirchner, Anthony Hoogs, Joshua Garland, Julia Hirschberg, Arslan Basharat, Huan Liu
Abstract: The rapid advancement of conversational agents, particularly chatbots powered by Large Language Models (LLMs), poses a significant risk of social engineering (SE) attacks on social media platforms. SE detection in multi-turn, chat-based interactions is considerably more complex than single-instance detection due to the dynamic nature of these conversations. A critical factor in mitigating this threat is understanding the SE attack mechanisms through which SE attacks operate, specifically how attackers exploit vulnerabilities and how victims' personality traits contribute to their susceptibility. In this work, we propose an LLM-agentic framework, SE-VSim, to simulate SE attack mechanisms by generating multi-turn conversations. We model victim agents with varying personality traits to assess how psychological profiles influence susceptibility to manipulation. Using a dataset of over 1000 simulated conversations, we examine attack scenarios in which adversaries, posing as recruiters, funding agencies, and journalists, attempt to extract sensitive information. Based on this analysis, we present a proof of concept, SE-OmniGuard, to offer personalized protection to users by leveraging prior knowledge of the victims personality, evaluating attack strategies, and monitoring information exchanges in conversations to identify potential SE attempts.
Authors: Luxi He, Xiangyu Qi, Michel Liao, Inyoung Cheong, Prateek Mittal, Danqi Chen, Peter Henderson
Abstract: The latest Audio Language Models (Audio LMs) process speech directly instead of relying on a separate transcription step. This shift preserves detailed information, such as intonation or the presence of multiple speakers, that would otherwise be lost in transcription. However, it also introduces new safety risks, including the potential misuse of speaker identity cues and other sensitive vocal attributes, which could have legal implications. In this paper, we urge a closer examination of how these models are built and deployed. Our experiments show that end-to-end modeling, compared with cascaded pipelines, creates socio-technical safety risks such as identity inference, biased decision-making, and emotion detection. This raises concerns about whether Audio LMs store voiceprints and function in ways that create uncertainty under existing legal regimes. We then argue that the Principle of Least Privilege should be considered to guide the development and deployment of these models. Specifically, evaluations should assess (1) the privacy and safety risks associated with end-to-end modeling; and (2) the appropriate scope of information access. Finally, we highlight related gaps in current audio LM benchmarks and identify key open research questions, both technical and policy-related, that must be addressed to enable the responsible deployment of end-to-end Audio LMs.
Authors: Qi Feng
Abstract: Video-based spatial cognition is vital for robotics and embodied AI but challenges current Vision-Language Models (VLMs). This paper makes two key contributions. First, we introduce ViCA (Visuospatial Cognitive Assistant)-322K, a diverse dataset of 322,003 QA pairs from real-world indoor videos (ARKitScenes, ScanNet, ScanNet++), offering supervision for 3D metadata-grounded queries and video-based complex reasoning. Second, we develop ViCA-7B, fine-tuned on ViCA-322K, which achieves new state-of-the-art on all eight VSI-Bench tasks, outperforming existing models, including larger ones (e.g., +26.1 on Absolute Distance). For interpretability, we present ViCA-Thinking-2.68K, a dataset with explicit reasoning chains, and fine-tune ViCA-7B to create ViCA-7B-Thinking, a model that articulates its spatial reasoning. Our work highlights the importance of targeted data and suggests paths for improved temporal-spatial modeling. We release all resources to foster research in robust visuospatial intelligence.
Authors: Qi Feng
Abstract: While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, visuospatial cognition - reasoning about spatial layouts, relations, and dynamics - remains a significant challenge. Existing models often lack the necessary architectural components and specialized training data for fine-grained spatial understanding. We introduce ViCA2 (Visuospatial Cognitive Assistant 2), a novel MLLM designed to enhance spatial reasoning. ViCA2 features a dual vision encoder architecture integrating SigLIP for semantics and Hiera for spatial structure, coupled with a token ratio control mechanism for efficiency. We also developed ViCA-322K, a new large-scale dataset with over 322,000 spatially grounded question-answer pairs for targeted instruction tuning. On the challenging VSI-Bench benchmark, our ViCA2-7B model achieves a state-of-the-art average score of 56.8, significantly surpassing larger open-source models (e.g., LLaVA-NeXT-Video-72B, 40.9) and leading proprietary models (Gemini-1.5 Pro, 45.4). This demonstrates the effectiveness of our approach in achieving strong visuospatial intelligence with a compact model. We release ViCA2, its codebase, and the ViCA-322K dataset to facilitate further research.
Authors: Debodeep Banerjee, Burcu Sayin, Stefano Teso, Andrea Passerini
Abstract: Medical decision-making is a critical task, where errors can result in serious, potentially life-threatening consequences. While full automation remains challenging, hybrid frameworks that combine machine intelligence with human oversight offer a practical alternative. In this paper, we present MedGellan, a lightweight, annotation-free framework that uses a Large Language Model (LLM) to generate clinical guidance from raw medical records, which is then used by a physician to predict diagnoses. MedGellan uses a Bayesian-inspired prompting strategy that respects the temporal order of clinical data. Preliminary experiments show that the guidance generated by the LLM with MedGellan improves diagnostic performance, particularly in recall and $F_1$ score.
Authors: Andrew Brown, Muhammad Roman, Barry Devereux
Abstract: This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 framework, we (i) specify explicit inclusion and exclusion criteria based on citation count and research questions, (ii) catalogue datasets, architectures, and evaluation practices, and (iii) synthesise empirical evidence on the effectiveness and limitations of RAG. To mitigate citation-lag bias, we applied a lower citation-count threshold to papers published in 2025 so that emerging breakthroughs with naturally fewer citations were still captured. This review clarifies the current research landscape, highlights methodological gaps, and charts priority directions for future research.
Authors: Rubing Chen, Jiaxin Wu, Jian Wang, Xulu Zhang, Wenqi Fan, Chenghua Lin, Xiao-Yong Wei, Qing Li
Abstract: The increasing demand for domain-specific evaluation of large language models (LLMs) has led to the development of numerous benchmarks. These efforts often adhere to the principle of data scaling, relying on large corpora or extensive question-answer (QA) sets to ensure broad coverage. However, the impact of corpus and QA set design on the precision and recall of domain-specific LLM performance remains poorly understood. In this paper, we argue that data scaling is not always the optimal principle for domain-specific benchmark construction. Instead, we introduce Comp-Comp, an iterative benchmarking framework grounded in the principle of comprehensiveness and compactness. Comprehensiveness ensures semantic recall by covering the full breadth of the domain, while compactness improves precision by reducing redundancy and noise. To demonstrate the effectiveness of our approach, we present a case study conducted at a well-renowned university, resulting in the creation of PolyBench, a large-scale, high-quality academic benchmark. Although this study focuses on academia, the Comp-Comp framework is domain-agnostic and readily adaptable to a wide range of specialized fields. The source code and datasets can be accessed at https://github.com/Anya-RB-Chen/COMP-COMP.
Authors: Xiaodong Cui, A F M Saif, Brian Kingsbury, Tianyi Chen
Abstract: Self-supervised pre-training using unlabeled data is widely used in automatic speech recognition. In this paper, we propose a new self-supervised pre-training approach to dealing with heterogeneous data. Instead of mixing all the data and minimizing the averaged global loss in the conventional way, we impose additional local constraints to ensure that the model optimizes each source of heterogeneous data to its local optimum after $K$-step gradient descent initialized from the model. We formulate this as a bilevel optimization problem, and use the first-order approximation method to solve the problem. We discuss its connection to model-agnostic meta learning. Experiments are carried out on self-supervised pre-training using multi-domain and multilingual datasets, demonstrating that the proposed approach can significantly improve the adaptivity of the self-supervised pre-trained model for the downstream supervised fine-tuning tasks.
Authors: Zhenyuan Chen, Chenxi Wang, Feng Zhang
Abstract: Remote sensing is critical for disaster monitoring, yet existing datasets lack temporal image pairs and detailed textual annotations. While single-snapshot imagery dominates current resources, it fails to capture dynamic disaster impacts over time. To address this gap, we introduce the Remote Sensing Change Caption (RSCC) dataset, a large-scale benchmark comprising 62,315 pre-/post-disaster image pairs (spanning earthquakes, floods, wildfires, and more) paired with rich, human-like change captions. By bridging the temporal and semantic divide in remote sensing data, RSCC enables robust training and evaluation of vision-language models for disaster-aware bi-temporal understanding. Our results highlight RSCC's ability to facilitate detailed disaster-related analysis, paving the way for more accurate, interpretable, and scalable vision-language applications in remote sensing. Code and dataset are available at https://github.com/Bili-Sakura/RSCC.
Authors: Kyra Wilson, Mattea Sim, Anna-Maria Gueorguieva, Aylin Caliskan
Abstract: In this study, we conduct a resume-screening experiment (N=528) where people collaborate with simulated AI models exhibiting race-based preferences (bias) to evaluate candidates for 16 high and low status occupations. Simulated AI bias approximates factual and counterfactual estimates of racial bias in real-world AI systems. We investigate people's preferences for White, Black, Hispanic, and Asian candidates (represented through names and affinity groups on quality-controlled resumes) across 1,526 scenarios and measure their unconscious associations between race and status using implicit association tests (IATs), which predict discriminatory hiring decisions but have not been investigated in human-AI collaboration. When making decisions without AI or with AI that exhibits no race-based preferences, people select all candidates at equal rates. However, when interacting with AI favoring a particular group, people also favor those candidates up to 90% of the time, indicating a significant behavioral shift. The likelihood of selecting candidates whose identities do not align with common race-status stereotypes can increase by 13% if people complete an IAT before conducting resume screening. Finally, even if people think AI recommendations are low quality or not important, their decisions are still vulnerable to AI bias under certain circumstances. This work has implications for people's autonomy in AI-HITL scenarios, AI and work, design and evaluation of AI hiring systems, and strategies for mitigating bias in collaborative decision-making tasks. In particular, organizational and regulatory policy should acknowledge the complex nature of AI-HITL decision making when implementing these systems, educating people who use them, and determining which are subject to oversight.
Authors: Xuan-Phi Nguyen, Shrey Pandit, Revanth Gangi Reddy, Austin Xu, Silvio Savarese, Caiming Xiong, Shafiq Joty
Abstract: Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances in reasoning-oriented (``thinking'') models. Such capabilities are key to unlocking a number of important applications. One such application is Deep Research (DR), which requires extensive search and reasoning over many sources. Our work in this paper focuses on the development of native Autonomous Single-Agent models for DR featuring minimal web crawling and Python tool integration. Unlike multi-agent systems, where agents take up pre-defined roles and are told what to do at each step in a static workflow, an autonomous single-agent determines its next action dynamically based on context, without manual directive. While prior work has proposed training recipes for base or instruction-tuned LLMs, we focus on continual reinforcement learning (RL) of reasoning-optimized models to further enhance agentic skills while preserving reasoning ability. Towards this end, we propose a simple RL recipe with entirely synthetic data, which we apply to various open-source LLMs. Our best variant SFR-DR-20B achieves up to 28.7% on Humanity's Last Exam benchmark. In addition, we conduct key analysis experiments to provide more insights into our methodologies.
Authors: Wenxuan Huang, Shuang Chen, Zheyong Xie, Shaosheng Cao, Shixiang Tang, Yufan Shen, Qingyu Yin, Wenbo Hu, Xiaoman Wang, Yuntian Tang, Junbo Qiao, Yue Guo, Yao Hu, Zhenfei Yin, Philip Torr, Yu Cheng, Wanli Ouyang, Shaohui Lin
Abstract: Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly couple comprehension with generation such as GPT-4o. Motivated by recent advances in interleaving reasoning, we explore whether such reasoning can further improve Text-to-Image (T2I) generation. We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis: the model first produces a text-based thinking to guide an initial image, then reflects on the result to refine fine-grained details, visual quality, and aesthetics while preserving semantics. To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals: (1) strengthening the initial think-and-generate stage to establish core content and base quality, and (2) enabling high-quality textual reflection and faithful implementation of those refinements in a subsequent image. We curate IRGL-300K, a dataset organized into six decomposed learning modes that jointly cover learning text-based thinking, and full thinking-image trajectories. Starting from a unified foundation model that natively emits interleaved text-image outputs, our two-stage training first builds robust thinking and reflection, then efficiently tunes the IRG pipeline in the full thinking-image trajectory data. Extensive experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN, alongside substantial improvements in visual quality and fine-grained fidelity. The code, model weights and datasets will be released in: https://github.com/Osilly/Interleaving-Reasoning-Generation .
URLs: https://github.com/Osilly/Interleaving-Reasoning-Generation