new Optimizing Performance: How Compact Models Match or Exceed GPT's Classification Capabilities through Fine-Tuning

Authors: Baptiste Lefort, Eric Benhamou, Jean-Jacques Ohana, David Saltiel, Beatrice Guez

Abstract: In this paper, we demonstrate that non-generative, small-sized models such as FinBERT and FinDRoBERTa, when fine-tuned, can outperform GPT-3.5 and GPT-4 models in zero-shot learning settings in sentiment analysis for financial news. These fine-tuned models show comparable results to GPT-3.5 when it is fine-tuned on the task of determining market sentiment from daily financial news summaries sourced from Bloomberg. To fine-tune and compare these models, we created a novel database, which assigns a market score to each piece of news without human interpretation bias, systematically identifying the mentioned companies and analyzing whether their stocks have gone up, down, or remained neutral. Furthermore, the paper shows that the assumptions of Condorcet's Jury Theorem do not hold suggesting that fine-tuned small models are not independent of the fine-tuned GPT models, indicating behavioural similarities. Lastly, the resulted fine-tuned models are made publicly available on HuggingFace, providing a resource for further research in financial sentiment analysis and text classification.

new Enriching Datasets with Demographics through Large Language Models: What's in a Name?

Authors: Khaled AlNuaimi, Gautier Marti, Mathieu Ravaut, Abdulla AlKetbi, Andreas Henschel, Raed Jaradat

Abstract: Enriching datasets with demographic information, such as gender, race, and age from names, is a critical task in fields like healthcare, public policy, and social sciences. Such demographic insights allow for more precise and effective engagement with target populations. Despite previous efforts employing hidden Markov models and recurrent neural networks to predict demographics from names, significant limitations persist: the lack of large-scale, well-curated, unbiased, publicly available datasets, and the lack of an approach robust across datasets. This scarcity has hindered the development of traditional supervised learning approaches. In this paper, we demonstrate that the zero-shot capabilities of Large Language Models (LLMs) can perform as well as, if not better than, bespoke models trained on specialized data. We apply these LLMs to a variety of datasets, including a real-life, unlabelled dataset of licensed financial professionals in Hong Kong, and critically assess the inherent demographic biases in these models. Our work not only advances the state-of-the-art in demographic enrichment but also opens avenues for future research in mitigating biases in LLMs.

new Multi-Document Grounded Multi-Turn Synthetic Dialog Generation

Authors: Young-Suk Lee, Chulaka Gunasekara, Danish Contractor, Ram\'on Fernandez Astudillo, Radu Florian

Abstract: We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with Chain-of-Thought (CoT) prompting. Second, we support the generation of multi-document grounded dialogs by mimicking real-world use of retrievers to update the grounding documents after every user-turn in the dialog. Third, we apply LLM-as-a-Judge to filter out queries with incorrect answers. Human evaluation of the synthetic dialog data suggests that the data is diverse, coherent, and includes mostly correct answers. Both human and automatic evaluations of answerable queries indicate that models fine-tuned on synthetic dialogs consistently out-perform those fine-tuned on existing human generated training data across four publicly available multi-turn document grounded benchmark test sets.

new Egalitarian Language Representation in Language Models: It All Begins with Tokenizers

Authors: Menan Velayuthan, Kengatharaiyer Sarveswaran

Abstract: Tokenizers act as a bridge between human language and the latent space of language models, influencing how language is represented in these models. Due to the immense popularity of English-Centric Large Language Models (LLMs), efforts are being made to adapt them for other languages. However, we demonstrate that, from a tokenization standpoint, not all tokenizers offer fair representation for complex script languages such as Tamil, Sinhala, and Hindi, primarily due to the choice of pre-tokenization methods. We go further to show that pre-tokenization plays a more critical role than the tokenization algorithm itself in achieving an egalitarian representation of these complex script languages. To address this, we introduce an improvement to the Byte Pair Encoding (BPE) algorithm by incorporating graphemes, which we term Grapheme Pair Encoding (GPE). Our experiments show that grapheme-based character extraction outperforms byte-level tokenizers for complex scripts. We validate this approach through experiments on Tamil, Sinhala, and Hindi.

new Chain-of-Thought Prompting for Speech Translation

Authors: Ke Hu, Zhehuai Chen, Chao-Han Huck Yang, Piotr \.Zelasko, Oleksii Hrinchuk, Vitaly Lavrukhin, Jagadeesh Balam, Boris Ginsburg

Abstract: Large language models (LLMs) have demonstrated remarkable advancements in language understanding and generation. Building on the success of text-based LLMs, recent research has adapted these models to use speech embeddings for prompting, resulting in Speech-LLM models that exhibit strong performance in automatic speech recognition (ASR) and automatic speech translation (AST). In this work, we propose a novel approach to leverage ASR transcripts as prompts for AST in a Speech-LLM built on an encoder-decoder text LLM. The Speech-LLM model consists of a speech encoder and an encoder-decoder structure Megatron-T5. By first decoding speech to generate ASR transcripts and subsequently using these transcripts along with encoded speech for prompting, we guide the speech translation in a two-step process like chain-of-thought (CoT) prompting. Low-rank adaptation (LoRA) is used for the T5 LLM for model adaptation and shows superior performance to full model fine-tuning. Experimental results show that the proposed CoT prompting significantly improves AST performance, achieving an average increase of 2.4 BLEU points across 6 En->X or X->En AST tasks compared to speech prompting alone. Additionally, compared to a related CoT prediction method that predicts a concatenated sequence of ASR and AST transcripts, our method performs better by an average of 2 BLEU points.

new Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs

Authors: Guillermo Marco, Luz Rello, Julio Gonzalo

Abstract: In this paper, we evaluate the creative fiction writing abilities of a fine-tuned small language model (SLM), BART Large, and compare its performance to humans and two large language models (LLMs): GPT-3.5 and GPT-4o. Our evaluation consists of two experiments: (i) a human evaluation where readers assess the stories generated by the SLM compared to human-written stories, and (ii) a qualitative linguistic analysis comparing the textual characteristics of the stories generated by the different models. In the first experiment, we asked 68 participants to rate short stories generated by the models and humans along dimensions such as grammaticality, relevance, creativity, and attractiveness. BART Large outperformed human writers in most aspects, except creativity, with an overall score of 2.11 compared to 1.85 for human-written texts -- a 14% improvement. In the second experiment, the qualitative analysis revealed that, while GPT-4o exhibited near-perfect internal and external coherence, it tended to produce more predictable narratives, with only 3% of its stories seen as novel. In contrast, 15% of BART's stories were considered novel, indicating a higher degree of creativity despite its smaller model size. This study provides both quantitative and qualitative insights into how model size and fine-tuning influence the balance between creativity, fluency, and coherence in creative writing tasks.

new Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey

Authors: Genta Indra Winata, Hanyang Zhao, Anirban Das, Wenpin Tang, David D. Yao, Shi-Xiong Zhang, Sambit Sahu

Abstract: Preference tuning is a crucial process for aligning deep generative models with human preferences. This survey offers a thorough overview of recent advancements in preference tuning and the integration of human feedback. The paper is organized into three main sections: 1) introduction and preliminaries: an introduction to reinforcement learning frameworks, preference tuning tasks, models, and datasets across various modalities: language, speech, and vision, as well as different policy approaches, 2) in-depth examination of each preference tuning approach: a detailed analysis of the methods used in preference tuning, and 3) applications, discussion, and future directions: an exploration of the applications of preference tuning in downstream tasks, including evaluation methods for different modalities, and an outlook on future research directions. Our objective is to present the latest methodologies in preference tuning and model alignment, enhancing the understanding of this field for researchers and practitioners. We hope to encourage further engagement and innovation in this area.

new HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection

Authors: Theo King, Zekun Wu, Adriano Koshiyama, Emre Kazim, Philip Treleaven

Abstract: Stereotypes are generalised assumptions about societal groups, and even state-of-the-art LLMs using in-context learning struggle to identify them accurately. Due to the subjective nature of stereotypes, where what constitutes a stereotype can vary widely depending on cultural, social, and individual perspectives, robust explainability is crucial. Explainable models ensure that these nuanced judgments can be understood and validated by human users, promoting trust and accountability. We address these challenges by introducing HEARTS (Holistic Framework for Explainable, Sustainable, and Robust Text Stereotype Detection), a framework that enhances model performance, minimises carbon footprint, and provides transparent, interpretable explanations. We establish the Expanded Multi-Grain Stereotype Dataset (EMGSD), comprising 57,201 labeled texts across six groups, including under-represented demographics like LGBTQ+ and regional stereotypes. Ablation studies confirm that BERT models fine-tuned on EMGSD outperform those trained on individual components. We then analyse a fine-tuned, carbon-efficient ALBERT-V2 model using SHAP to generate token-level importance values, ensuring alignment with human understanding, and calculate explainability confidence scores by comparing SHAP and LIME outputs. Finally, HEARTS is applied to assess stereotypical bias in 12 LLM outputs, revealing a gradual reduction in bias over time within model families.

new ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering

Authors: Priyesh Vakharia, Abigail Kufeldt, Max Meyers, Ian Lane, Leilani Gilpin

Abstract: Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language models (LLMs). We propose \systemname{}, a novel neurosymbolic framework, to improve the robustness and reliability of LLMs in question-answering tasks. We provide \systemname{} with a domain-specific knowledge base, a logical reasoning system, and an integration to an existing LLM. This framework has two capabilities (1) context gathering: generating explainable and relevant context for a given query, and (2) validation: confirming and validating the factual accuracy of a statement in accordance with a knowledge base (KB). Our work opens a new area of neurosymbolic generative AI text validation and user personalization.

new "A Woman is More Culturally Knowledgeable than A Man?": The Effect of Personas on Cultural Norm Interpretation in LLMs

Authors: Mahammed Kamruzzaman, Hieu Nguyen, Nazmul Hassan, Gene Louis Kim

Abstract: As the deployment of large language models (LLMs) expands, there is an increasing demand for personalized LLMs. One method to personalize and guide the outputs of these models is by assigning a persona -- a role that describes the expected behavior of the LLM (e.g., a man, a woman, an engineer). This study investigates whether an LLM's understanding of social norms varies across assigned personas. Ideally, the perception of a social norm should remain consistent regardless of the persona, since acceptability of a social norm should be determined by the region the norm originates from, rather than by individual characteristics such as gender, body size, or race. A norm is universal within its cultural context. In our research, we tested 36 distinct personas from 12 sociodemographic categories (e.g., age, gender, beauty) across four different LLMs. We find that LLMs' cultural norm interpretation varies based on the persona used and the norm interpretation also varies within a sociodemographic category (e.g., a fat person and a thin person as in physical appearance group) where an LLM with the more socially desirable persona (e.g., a thin person) interprets social norms more accurately than with the less socially desirable persona (e.g., a fat person). We also discuss how different types of social biases may contribute to the results that we observe.

new BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla

Authors: Mahammed Kamruzzaman, Abdullah Al Monsur, Shrabon Das, Enamul Hassan, Gene Louis Kim

Abstract: This study presents BanStereoSet, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and Kamruzzaman et. al.'s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This dataset not only serves as a crucial tool for measuring bias in multilingual LLMs but also facilitates the exploration of stereotypical bias across different social categories, potentially guiding the development of more equitable language technologies in Bangladeshi contexts. Our analysis of several language models using this dataset indicates significant biases, reinforcing the necessity for culturally and linguistically adapted datasets to develop more equitable language technologies.

new RUIE: Retrieval-based Unified Information Extraction using Large Language Model

Authors: Xincheng Liao, Junwen Duan, Yixi Huang, Jianxin Wang

Abstract: Unified information extraction (UIE) aims to complete all information extraction tasks using a single model or framework. While previous work has primarily focused on instruction-tuning large language models (LLMs) with constructed datasets, these methods require significant computational resources and struggle to generalize to unseen tasks. To address these limitations, we propose RUIE (Retrieval-based Unified Information Extraction), a framework that leverages in-context learning to enable rapid generalization while reducing computational costs. The key challenge in RUIE is selecting the most beneficial demonstrations for LLMs to effectively handle diverse IE tasks. To achieve this, we integrate LLM preferences for ranking candidate demonstrations and design a keyword-enhanced reward model to capture fine-grained relationships between queries and demonstrations. We then train a bi-encoder retriever for UIE through contrastive learning and knowledge distillation. To the best of our knowledge, RUIE is the first trainable retrieval framework for UIE. Experimental results on 8 held-out datasets demonstrate RUIE's effectiveness in generalizing to unseen tasks, with average F1-score improvements of 19.22 and 3.13 compared to instruction-tuning methods and other retrievers, respectively. Further analysis confirms RUIE's adaptability to LLMs of varying sizes and the importance of its key components.

new Enhancing Complex Formula Recognition with Hierarchical Detail-Focused Network

Authors: Jiale Wang, Junhui Yu, Huanyong Liu, Chenanran Kong

Abstract: Hierarchical and complex Mathematical Expression Recognition (MER) is challenging due to multiple possible interpretations of a formula, complicating both parsing and evaluation. In this paper, we introduce the Hierarchical Detail-Focused Recognition dataset (HDR), the first dataset specifically designed to address these issues. It consists of a large-scale training set, HDR-100M, offering an unprecedented scale and diversity with one hundred million training instances. And the test set, HDR-Test, includes multiple interpretations of complex hierarchical formulas for comprehensive model performance evaluation. Additionally, the parsing of complex formulas often suffers from errors in fine-grained details. To address this, we propose the Hierarchical Detail-Focused Recognition Network (HDNet), an innovative framework that incorporates a hierarchical sub-formula module, focusing on the precise handling of formula details, thereby significantly enhancing MER performance. Experimental results demonstrate that HDNet outperforms existing MER models across various datasets.

new Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation

Authors: Chunliang Tao, Xiaojing Fan, Yahe Yang

Abstract: As Large Language Models (LLMs) advance in natural language processing, there is growing interest in leveraging their capabilities to simplify software interactions. In this paper, we propose a novel system that integrates LLMs for both classifying natural language inputs into corresponding API calls and automating the creation of sample datasets tailored to specific API functions. By classifying natural language commands, our system allows users to invoke complex software functionalities through simple inputs, improving interaction efficiency and lowering the barrier to software utilization. Our dataset generation approach also enables the efficient and systematic evaluation of different LLMs in classifying API calls, offering a practical tool for developers or business owners to assess the suitability of LLMs for customized API management. We conduct experiments on several prominent LLMs using generated sample datasets for various API functions. The results show that GPT-4 achieves a high classification accuracy of 0.996, while LLaMA-3-8B performs much worse at 0.759. These findings highlight the potential of LLMs to transform API management and validate the effectiveness of our system in guiding model testing and selection across diverse applications.

new From Lists to Emojis: How Format Bias Affects Model Alignment

Authors: Xuanchang Zhang, Wei Xiong, Lichang Chen, Tianyi Zhou, Heng Huang, Tong Zhang

Abstract: In this paper, we study format biases in reinforcement learning from human feedback (RLHF). We observe that many widely-used preference models, including human evaluators, GPT-4, and top-ranking models on the RewardBench benchmark, exhibit strong biases towards specific format patterns, such as lists, links, bold text, and emojis. Furthermore, large language models (LLMs) can exploit these biases to achieve higher rankings on popular benchmarks like AlpacaEval and LMSYS Chatbot Arena. One notable example of this is verbosity bias, where current preference models favor longer responses that appear more comprehensive, even when their quality is equal to or lower than shorter, competing responses. However, format biases beyond verbosity remain largely underexplored in the literature. In this work, we extend the study of biases in preference learning beyond the commonly recognized length bias, offering a comprehensive analysis of a wider range of format biases. Additionally, we show that with a small amount of biased data (less than 1%), we can inject significant bias into the reward model. Moreover, these format biases can also be easily exploited by downstream alignment algorithms, such as best-of-n sampling and online iterative DPO, as it is usually easier to manipulate the format than to improve the quality of responses. Our findings emphasize the need to disentangle format and content both for designing alignment algorithms and evaluating models.

new TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning

Authors: Xinyuan Lu, Liangming Pan, Yubo Ma, Preslav Nakov, Min-Yen Kan

Abstract: Current Large Language Models (LLMs) exhibit limited ability to understand table structures and to apply precise numerical reasoning, which is crucial for tasks such as table question answering (TQA) and table-based fact verification (TFV). To address these challenges, we introduce our Tool-Augmented Reasoning framework for Tables (TART), which integrates LLMs with specialized tools. TART contains three key components: a table formatter to ensure accurate data representation, a tool maker to develop specific computational tools, and an explanation generator to maintain explainability. We also present the TOOLTAB dataset, a new benchmark designed specifically for training LLMs in table-tool integration. Our experiments indicate that TART achieves substantial improvements over existing methods (e.g., Chain-of-Thought) by improving both the precision of data processing and the clarity of the reasoning process. Notably, TART paired with CodeLlama achieves 90.0% of the accuracy of the closed-sourced LLM GPT-3.5-turbo, highlighting its robustness in diverse real-world scenarios. All the code and data are available at https://github.com/XinyuanLu00/TART.

URLs: https://github.com/XinyuanLu00/TART.

new Revealing the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing

Authors: Wenyuan Zhang, Jiawei Sheng, Shuaiyi Nie, Zefeng Zhang, Xinghua Zhang, Yongquan He, Tingwen Liu

Abstract: Large language model (LLM) role-playing has gained widespread attention, where the authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose a probing dataset to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to effectively detect these two types of errors, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S2RD), to further explore the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.

new Enabling Real-Time Conversations with Minimal Training Costs

Authors: Wang Xu, Shuo Wang, Weilin Zhao, Xu Han, Yukun Yan, Yudi Zhang, Zhe Tao, Zhiyuan Liu, Wanxiang Che

Abstract: Large language models (LLMs) have demonstrated the ability to improve human efficiency through conversational interactions. Conventional LLM-powered dialogue systems, operating on a turn-based paradigm, preclude real-time interaction during response generation. To address this limitation, researchers have proposed duplex models. These models can dynamically adapt to user input, facilitating real-time interactive feedback. However, these methods typically require substantial computational resources to acquire the ability. To reduce overhead, this paper presents a new duplex decoding approach that enhances LLMs with duplex ability, requiring minimal additional training. Specifically, our method employs parallel decoding of queries and responses in conversations, effectively implementing a channel-division-multiplexing decoding strategy. Experimental results indicate that our proposed method significantly enhances the naturalness and human-likeness of user-AI interactions with minimal training costs.

new Human-like Affective Cognition in Foundation Models

Authors: Kanishk Gandhi, Zoe Lynch, Jan-Philipp Fr\"anken, Kayla Patterson, Sharon Wambu, Tobias Gerstenberg, Desmond C. Ong, Noah D. Goodman

Abstract: Understanding emotions is fundamental to human interaction and experience. Humans easily infer emotions from situations or facial expressions, situations from emotions, and do a variety of other \emph{affective cognition}. How adept is modern AI at these inferences? We introduce an evaluation framework for testing affective cognition in foundation models. Starting from psychological theory, we generate 1,280 diverse scenarios exploring relationships between appraisals, emotions, expressions, and outcomes. We evaluate the abilities of foundation models (GPT-4, Claude-3, Gemini-1.5-Pro) and humans (N = 567) across carefully selected conditions. Our results show foundation models tend to agree with human intuitions, matching or exceeding interparticipant agreement. In some conditions, models are ``superhuman'' -- they better predict modal human judgements than the average human. All models benefit from chain-of-thought reasoning. This suggests foundation models have acquired a human-like understanding of emotions and their influence on beliefs and behavior.

new Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources

Authors: Issey Sukeda

Abstract: The recent success of large language models (LLMs) and the scaling law has led to a widespread adoption of larger models. Particularly in the healthcare industry, there is an increasing demand for locally operated LLMs due to security concerns. However, the majority of high quality open-source LLMs have a size of 70B parameters, imposing significant financial burdens on users for GPU preparation and operation. To overcome these issues, we present a medical adaptation based on the recent 7B models, which enables the operation in low computational resources. We compare the performance on medical question-answering benchmarks in two languages (Japanese and English), demonstrating that its scores reach parity with or surpass those of currently existing medical LLMs that are ten times larger. We find that fine-tuning an English-centric base model on Japanese medical dataset improves the score in both language, supporting the effect of cross-lingual knowledge transfer. We hope that this study will alleviate financial challenges, serving as a stepping stone for clinical institutions to practically utilize LLMs locally. Our evaluation code is available at https://huggingface.co/stardust-coder/jmedllm-7b-v1.

URLs: https://huggingface.co/stardust-coder/jmedllm-7b-v1.

new The Factuality of Large Language Models in the Legal Domain

Authors: Rajaa El Hamdani, Thomas Bonald, Fragkiskos Malliaros, Nils Holzenberger, Fabian Suchanek

Abstract: This paper investigates the factuality of large language models (LLMs) as knowledge bases in the legal domain, in a realistic usage scenario: we allow for acceptable variations in the answer, and let the model abstain from answering when uncertain. First, we design a dataset of diverse factual questions about case law and legislation. We then use the dataset to evaluate several LLMs under different evaluation methods, including exact, alias, and fuzzy matching. Our results show that the performance improves significantly under the alias and fuzzy matching methods. Further, we explore the impact of abstaining and in-context examples, finding that both strategies enhance precision. Finally, we demonstrate that additional pre-training on legal documents, as seen with SaulLM, further improves factual precision from 63% to 81%.

new Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework

Authors: Yuping Wu, Hao Li, Hongbo Zhu, Goran Nenadic, Xiao-Jun Zeng

Abstract: Extract-then-Abstract is a naturally coherent paradigm to conduct abstractive summarization with the help of salient information identified by the extractive model. Previous works that adopt this paradigm train the extractor and abstractor separately and introduce extra parameters to highlight the extracted salients to the abstractor, which results in error accumulation and additional training costs. In this paper, we first introduce a parameter-free highlight method into the encoder-decoder framework: replacing the encoder attention mask with a saliency mask in the cross-attention module to force the decoder to focus only on salient parts of the input. A preliminary analysis compares different highlight methods, demonstrating the effectiveness of our saliency mask. We further propose the novel extract-and-abstract paradigm, ExtAbs, which jointly and seamlessly performs Extractive and Abstractive summarization tasks within single encoder-decoder model to reduce error accumulation. In ExtAbs, the vanilla encoder is augmented to extract salients, and the vanilla decoder is modified with the proposed saliency mask to generate summaries. Built upon BART and PEGASUS, experiments on three datasets show that ExtAbs can achieve superior performance than baselines on the extractive task and performs comparable, or even better than the vanilla models on the abstractive task.

new MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts

Authors: Tianle Gu, Kexin Huang, Ruilin Luo, Yuanqi Yao, Yujiu Yang, Yan Teng, Yingchun Wang

Abstract: Large Language Models (LLMs) can memorize sensitive information, raising concerns about potential misuse. LLM Unlearning, a post-hoc approach to remove this information from trained LLMs, offers a promising solution to mitigate these risks. However, previous practices face three key challenges: 1. Utility: successful unlearning often causes catastrophic collapse on unrelated tasks. 2. Efficiency: many methods either involve adding similarly sized models, which slows down unlearning or inference, or require retain data that are difficult to obtain. 3. Robustness: even effective methods may still leak data via extraction techniques. To address these challenges, we propose MEOW, a simple yet effective gradient descent-based unlearning method. Specifically, we use an offline LLM to generate a set of inverted facts. Then, we design a new metric, MEMO, to quantify memorization in LLMs. Finally, based on the signals provided by MEMO, we select the most appropriate set of inverted facts and finetune the model based on them. We evaluate MEOW on the commonly used unlearn benchmark, ToFU, with Llama2-7B-Chat and Phi-1.5B, and test it on both NLU and NLG tasks. Results demonstrate significant improvement of MEOW in forget quality without substantial loss in model utility. Meanwhile, MEOW does not exhibit significant degradation in NLU or NLG capabilities, and there is even a slight improvement in NLU performance.

new DocMamba: Efficient Document Pre-training with State Space Model

Authors: Pengfei Hu, Zhenrong Zhang, Jiefeng Ma, Shuhang Liu, Jun Du, Jianshu Zhang

Abstract: In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the self-attention mechanism's quadratic computational complexity hinders their efficiency and ability to process long documents. In this paper, we present DocMamba, a novel framework based on the state space model. It is designed to reduce computational complexity to linear while preserving global modeling capabilities. To further enhance its effectiveness in document processing, we introduce the Segment-First Bidirectional Scan (SFBS) to capture contiguous semantic information. Experimental results demonstrate that DocMamba achieves new state-of-the-art results on downstream datasets such as FUNSD, CORD, and SORIE, while significantly improving speed and reducing memory usage. Notably, experiments on the HRDoc confirm DocMamba's potential for length extrapolation. The code will be available online.

new LLMs + Persona-Plug = Personalized LLMs

Authors: Jiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei, Erxue Min, Yu Lu, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

Abstract: Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. Some of them involve fine-tuning a unique personalized LLM for each user, which is too expensive for widespread application. Alternative approaches introduce personalization information in a plug-and-play manner by retrieving the user's relevant historical texts as demonstrations. However, this retrieval-based strategy may break the continuity of the user history and fail to capture the user's overall styles and patterns, hence leading to sub-optimal performance. To address these challenges, we propose a novel personalized LLM model, \ours{}. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module. By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their own parameters. Extensive experiments on various tasks in the language model personalization (LaMP) benchmark demonstrate that the proposed model significantly outperforms existing personalized LLM approaches.

new LLMs in Education: Novel Perspectives, Challenges, and Opportunities

Authors: Bashar Alhafni, Sowmya Vajjala, Stefano Bann\`o, Kaushal Kumar Maurya, Ekaterina Kochmar

Abstract: The role of large language models (LLMs) in education is an increasing area of interest today, considering the new opportunities they offer for teaching, learning, and assessment. This cutting-edge tutorial provides an overview of the educational applications of NLP and the impact that the recent advances in LLMs have had on this field. We will discuss the key challenges and opportunities presented by LLMs, grounding them in the context of four major educational applications: reading, writing, and speaking skills, and intelligent tutoring systems (ITS). This COLING 2025 tutorial is designed for researchers and practitioners interested in the educational applications of NLP and the role LLMs have to play in this area. It is the first of its kind to address this timely topic.

new Efficacy of Synthetic Data as a Benchmark

Authors: Gaurav Maheshwari, Dmitry Ivanov, Kevin El Haddad

Abstract: Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is essential to understand how representative they are of real-world data. We investigate this by assessing the effectiveness of generating synthetic data through LLM and using it as a benchmark for various NLP tasks. Our experiments across six datasets, and three different tasks, show that while synthetic data can effectively capture performance of various methods for simpler tasks, such as intent classification, it falls short for more complex tasks like named entity recognition. Additionally, we propose a new metric called the bias factor, which evaluates the biases introduced when the same LLM is used to both generate benchmarking data and to perform the tasks. We find that smaller LLMs exhibit biases towards their own generated data, whereas larger models do not. Overall, our findings suggest that the effectiveness of synthetic data as a benchmark varies depending on the task, and that practitioners should rely on data generated from multiple larger models whenever possible.

new Sampling Latent Material-Property Information From LLM-Derived Embedding Representations

Authors: Luke P. J. Gilligan, Matteo Cobelli, Hasan M. Sayeed, Taylor D. Sparks, Stefano Sanvito

Abstract: Vector embeddings derived from large language models (LLMs) show promise in capturing latent information from the literature. Interestingly, these can be integrated into material embeddings, potentially useful for data-driven predictions of materials properties. We investigate the extent to which LLM-derived vectors capture the desired information and their potential to provide insights into material properties without additional training. Our findings indicate that, although LLMs can be used to generate representations reflecting certain property information, extracting the embeddings requires identifying the optimal contextual clues and appropriate comparators. Despite this restriction, it appears that LLMs still have the potential to be useful in generating meaningful materials-science representations.

new ASR Benchmarking: Need for a More Representative Conversational Dataset

Authors: Gaurav Maheshwari, Dmitry Ivanov, Th\'eo Johannet, Kevin El Haddad

Abstract: Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational environments, where speech is often unstructured and contains disfluencies such as pauses, interruptions, and diverse accents. In this study, we introduce a multilingual conversational dataset, derived from TalkBank, consisting of unstructured phone conversation between adults. Our results show a significant performance drop across various state-of-the-art ASR models when tested in conversational settings. Furthermore, we observe a correlation between Word Error Rate and the presence of speech disfluencies, highlighting the critical need for more realistic, conversational ASR benchmarks.

new Using Large Language Models to Generate Clinical Trial Tables and Figures

Authors: Yumeng Yang, Peter Krusche, Kristyn Pantoja, Cheng Shi, Ethan Ludmir, Kirk Roberts, Gen Zhu

Abstract: Tables, figures, and listings (TFLs) are essential tools for summarizing clinical trial data. Creation of TFLs for reporting activities is often a time-consuming task encountered routinely during the execution of clinical trials. This study explored the use of large language models (LLMs) to automate the generation of TFLs through prompt engineering and few-shot transfer learning. Using public clinical trial data in ADaM format, our results demonstrated that LLMs can efficiently generate TFLs with prompt instructions, showcasing their potential in this domain. Furthermore, we developed a conservational agent named Clinical Trial TFL Generation Agent: An app that matches user queries to predefined prompts that produce customized programs to generate specific predefined TFLs.

new Dual-Layer Training and Decoding of Large Language Model with Simultaneously Thinking and Speaking

Authors: Ningyuan Xi, Xiaoyu Wang, Yetao Wu, Teng Chen, Qingqing Gu, Jinxian Qu, Zhonglin Jiang, Yong Chen, Luo Ji

Abstract: Large Language Model can reasonably understand and generate human expressions but may lack of thorough thinking and reasoning mechanisms. Recently there have been several studies which enhance the thinking ability of language models but most of them are not data-driven or training-based. In this paper, we are motivated by the cognitive mechanism in the natural world, and design a novel model architecture called TaS which allows it to first consider the thoughts and then express the response based upon the query. We design several pipelines to annotate or generate the thought contents from prompt-response samples, then add language heads in a middle layer which behaves as the thinking layer. We train the language model by the thoughts-augmented data and successfully let the thinking layer automatically generate reasonable thoughts and finally output more reasonable responses. Both qualitative examples and quantitative results validate the effectiveness and performance of TaS. Our code is available at https://anonymous.4open.science/r/TadE.

URLs: https://anonymous.4open.science/r/TadE.

new PARAPHRASUS : A Comprehensive Benchmark for Evaluating Paraphrase Detection Models

Authors: Andrianos Michail, Simon Clematide, Juri Opitz

Abstract: The task of determining whether two texts are paraphrases has long been a challenge in NLP. However, the prevailing notion of paraphrase is often quite simplistic, offering only a limited view of the vast spectrum of paraphrase phenomena. Indeed, we find that evaluating models in a paraphrase dataset can leave uncertainty about their true semantic understanding. To alleviate this, we release paraphrasus, a benchmark designed for multi-dimensional assessment of paraphrase detection models and finer model selection. We find that paraphrase detection models under a fine-grained evaluation lens exhibit trade-offs that cannot be captured through a single classification dataset.

new Skill matching at scale: freelancer-project alignment for efficient multilingual candidate retrieval

Authors: Warren Jouanneau, Marc Palyart, Emma Jouffroy

Abstract: Finding the perfect match between a job proposal and a set of freelancers is not an easy task to perform at scale, especially in multiple languages. In this paper, we propose a novel neural retriever architecture that tackles this problem in a multilingual setting. Our method encodes project descriptions and freelancer profiles by leveraging pre-trained multilingual language models. The latter are used as backbone for a custom transformer architecture that aims to keep the structure of the profiles and project. This model is trained with a contrastive loss on historical data. Thanks to several experiments, we show that this approach effectively captures skill matching similarity and facilitates efficient matching, outperforming traditional methods.

new Measuring Human and AI Values based on Generative Psychometrics with Large Language Models

Authors: Haoran Ye, Yuhang Xie, Yuanyi Ren, Hanjun Fang, Xin Zhang, Guojie Song

Abstract: Human values and their measurement are long-standing interdisciplinary inquiry. Recent advances in AI have sparked renewed interest in this area, with large language models (LLMs) emerging as both tools and subjects of value measurement. This work introduces Generative Psychometrics for Values (GPV), an LLM-based, data-driven value measurement paradigm, theoretically grounded in text-revealed selective perceptions. We begin by fine-tuning an LLM for accurate perception-level value measurement and verifying the capability of LLMs to parse texts into perceptions, forming the core of the GPV pipeline. Applying GPV to human-authored blogs, we demonstrate its stability, validity, and superiority over prior psychological tools. Then, extending GPV to LLM value measurement, we advance the current art with 1) a psychometric methodology that measures LLM values based on their scalable and free-form outputs, enabling context-specific measurement; 2) a comparative analysis of measurement paradigms, indicating response biases of prior methods; and 3) an attempt to bridge LLM values and their safety, revealing the predictive power of different value systems and the impacts of various values on LLM safety. Through interdisciplinary efforts, we aim to leverage AI for next-generation psychometrics and psychometrics for value-aligned AI.

new Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Authors: An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, Keming Lu, Mingfeng Xue, Runji Lin, Tianyu Liu, Xingzhang Ren, Zhenru Zhang

Abstract: In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in integrating the philosophy of self-improvement throughout the entire pipeline, from pre-training and post-training to inference: (1) During the pre-training phase, Qwen2-Math-Instruct is utilized to generate large-scale, high-quality mathematical data. (2) In the post-training phase, we develop a reward model (RM) by conducting massive sampling from Qwen2-Math-Instruct. This RM is then applied to the iterative evolution of data in supervised fine-tuning (SFT). With a stronger SFT model, it's possible to iteratively train and update the RM, which in turn guides the next round of SFT data iteration. On the final SFT model, we employ the ultimate RM for reinforcement learning, resulting in the Qwen2.5-Math-Instruct. (3) Furthermore, during the inference stage, the RM is used to guide sampling, optimizing the model's performance. Qwen2.5-Math-Instruct supports both Chinese and English, and possess advanced mathematical reasoning capabilities, including Chain-of-Thought (CoT) and Tool-Integrated Reasoning (TIR). We evaluate our models on 10 mathematics datasets in both English and Chinese, such as GSM8K, MATH, GaoKao, AMC23, and AIME24, covering a range of difficulties from grade school level to math competition problems.

new Linguini: A benchmark for language-agnostic linguistic reasoning

Authors: Eduardo S\'anchez, Belen Alastruey, Christophe Ropers, Pontus Stenetorp, Mikel Artetxe, Marta R. Costa-juss\`a

Abstract: We propose a new benchmark to measure a language model's linguistic reasoning skills without relying on pre-existing language-specific knowledge. The test covers 894 questions grouped in 160 problems across 75 (mostly) extremely low-resource languages, extracted from the International Linguistic Olympiad corpus. To attain high accuracy on this benchmark, models don't need previous knowledge of the tested language, as all the information needed to solve the linguistic puzzle is presented in the context. We find that, while all analyzed models rank below 25% accuracy, there is a significant gap between open and closed models, with the best-performing proprietary model at 24.05% and the best-performing open model at 8.84%.

new BERT-VBD: Vietnamese Multi-Document Summarization Framework

Authors: Tuan-Cuong Vuong, Trang Mai Xuan, Thien Van Luong

Abstract: In tackling the challenge of Multi-Document Summarization (MDS), numerous methods have been proposed, spanning both extractive and abstractive summarization techniques. However, each approach has its own limitations, making it less effective to rely solely on either one. An emerging and promising strategy involves a synergistic fusion of extractive and abstractive summarization methods. Despite the plethora of studies in this domain, research on the combined methodology remains scarce, particularly in the context of Vietnamese language processing. This paper presents a novel Vietnamese MDS framework leveraging a two-component pipeline architecture that integrates extractive and abstractive techniques. The first component employs an extractive approach to identify key sentences within each document. This is achieved by a modification of the pre-trained BERT network, which derives semantically meaningful phrase embeddings using siamese and triplet network structures. The second component utilizes the VBD-LLaMA2-7B-50b model for abstractive summarization, ultimately generating the final summary document. Our proposed framework demonstrates a positive performance, attaining ROUGE-2 scores of 39.6% on the VN-MDS dataset and outperforming the state-of-the-art baselines.

new GRIN: GRadient-INformed MoE

Authors: Liyuan Liu, Young Jin Kim, Shuohang Wang, Chen Liang, Yelong Shen, Hao Cheng, Xiaodong Liu, Masahiro Tanaka, Xiaoxia Wu, Wenxiang Hu, Vishrav Chaudhary, Zeqi Lin, Chenruidong Zhang, Jilong Xue, Hany Awadalla, Jianfeng Gao, Weizhu Chen

Abstract: Mixture-of-Experts (MoE) models scale more effectively than dense models due to sparse computation through expert routing, selectively activating only a small subset of expert modules. However, sparse computation challenges traditional training practices, as discrete expert routing hinders standard backpropagation and thus gradient-based optimization, which are the cornerstone of deep learning. To better pursue the scaling power of MoE, we introduce GRIN (GRadient-INformed MoE training), which incorporates sparse gradient estimation for expert routing and configures model parallelism to avoid token dropping. Applying GRIN to autoregressive language modeling, we develop a top-2 16$\times$3.8B MoE model. Our model, with only 6.6B activated parameters, outperforms a 7B dense model and matches the performance of a 14B dense model trained on the same data. Extensive evaluations across diverse tasks demonstrate the potential of GRIN to significantly enhance MoE efficacy, achieving 79.4 on MMLU, 83.7 on HellaSwag, 74.4 on HumanEval, and 58.9 on MATH.

new MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning

Authors: Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal

Abstract: Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. While these improve performance, they often reach a saturation point. Refinement offers an alternative by using LLM-generated feedback to improve solution quality. However, refinement introduces 3 key challenges: (1) Excessive refinement: Uniformly refining all instances can over-correct and reduce the overall performance. (2) Inability to localize and address errors: LLMs have a limited ability to self-correct and struggle to identify and correct their own mistakes. (3) Insufficient refinement: Deciding how many iterations of refinement are needed is non-trivial, and stopping too soon could leave errors unaddressed. To tackle these issues, we propose MAgICoRe, which avoids excessive refinement by categorizing problem difficulty as easy or hard, solving easy problems with coarse-grained aggregation and hard ones with fine-grained and iterative multi-agent refinement. To improve error localization, we incorporate external step-wise reward model (RM) scores. Moreover, to ensure effective refinement, we employ a multi-agent loop with three agents: Solver, Reviewer (which generates targeted feedback based on step-wise RM scores), and the Refiner (which incorporates feedback). To ensure sufficient refinement, we re-evaluate updated solutions, iteratively initiating further rounds of refinement. We evaluate MAgICoRe on Llama-3-8B and GPT-3.5 and show its effectiveness across 5 math datasets. Even one iteration of MAgICoRe beats Self-Consistency by 3.4%, Best-of-k by 3.2%, and Self-Refine by 4.0% while using less than half the samples. Unlike iterative refinement with baselines, MAgICoRe continues to improve with more iterations. Finally, our ablations highlight the importance of MAgICoRe's RMs and multi-agent communication.

new You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL

Authors: Hideo Kobayashi, Wuwei Lan, Peng Shi, Shuaichen Chang, Jiang Guo, Henghui Zhu, Zhiguo Wang, Patrick Ng

Abstract: While significant progress has been made on the text-to-SQL task, recent solutions repeatedly encode the same database schema for every question, resulting in unnecessary high inference cost and often overlooking crucial database knowledge. To address these issues, we propose You Only Read Once (YORO), a novel paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference. YORO significantly reduces the input token length by 66%-98%. Despite its shorter inputs, our empirical results demonstrate YORO's competitive performances with traditional systems on three benchmarks as well as its significant outperformance on large databases. Furthermore, YORO excels in handling questions with challenging value retrievals such as abbreviation.

new Finetuning Language Models to Emit Linguistic Expressions of Uncertainty

Authors: Arslan Chaudhry, Sridhar Thiagarajan, Dilan Gorur

Abstract: Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these inaccuracies appear confident and convincing. As a result, end-users struggle to consistently align the confidence expressed by LLMs with the accuracy of their predictions, often leading to either blind trust in all outputs or a complete disregard for their reliability. In this work, we explore supervised finetuning on uncertainty-augmented predictions as a method to develop models that produce linguistic expressions of uncertainty. Specifically, we measure the calibration of pre-trained models and then fine-tune language models to generate calibrated linguistic expressions of uncertainty. Through experiments on various question-answering datasets, we demonstrate that LLMs are well-calibrated in assessing their predictions, and supervised finetuning based on the model's own confidence leads to well-calibrated expressions of uncertainty, particularly for single-claim answers.

new A Controlled Study on Long Context Extension and Generalization in LLMs

Authors: Yi Lu, Jing Nathan Yan, Songlin Yang, Justin T. Chiu, Siyu Ren, Fei Yuan, Wenting Zhao, Zhiyong Wu, Alexander M. Rush

Abstract: Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for extending models to handle long contexts. However, owing to differences in data and model classes, it has been challenging to compare these approaches, leading to uncertainty as to how to evaluate long-context performance and whether it differs from standard evaluation. We implement a controlled protocol for extension methods with a standardized evaluation, utilizing consistent base models and extension data. Our study yields several insights into long-context behavior. First, we reaffirm the critical role of perplexity as a general-purpose performance indicator even in longer-context tasks. Second, we find that current approximate attention methods systematically underperform across long-context tasks. Finally, we confirm that exact fine-tuning based methods are generally effective within the range of their extension, whereas extrapolation remains challenging. All codebases, models, and checkpoints will be made available open-source, promoting transparency and facilitating further research in this critical area of AI development.

new To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Authors: Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, Greg Durrett

Abstract: Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thinking'' really helpful? To analyze this, we conducted a quantitative meta-analysis covering over 100 papers using CoT and ran our own evaluations of 20 datasets across 14 models. Our results show that CoT gives strong performance benefits primarily on tasks involving math or logic, with much smaller gains on other types of tasks. On MMLU, directly generating the answer without CoT leads to almost identical accuracy as CoT unless the question or model's response contains an equals sign, indicating symbolic operations and reasoning. Following this finding, we analyze the behavior of CoT on these problems by separating planning and execution and comparing against tool-augmented LLMs. Much of CoT's gain comes from improving symbolic execution, but it underperforms relative to using a symbolic solver. Our results indicate that CoT can be applied selectively, maintaining performance while saving inference costs. Furthermore, they suggest a need to move beyond prompt-based CoT to new paradigms that better leverage intermediate computation across the whole range of LLM applications.

new Qwen2.5-Coder Technical Report

Authors: Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Kai Dang, An Yang, Rui Men, Fei Huang, Xingzhang Ren, Xuancheng Ren, Jingren Zhou, Junyang Lin

Abstract: In this report, we introduce the Qwen2.5-Coder series, a significant upgrade from its predecessor, CodeQwen1.5. This series includes two models: Qwen2.5-Coder-1.5B and Qwen2.5-Coder-7B. As a code-specific model, Qwen2.5-Coder is built upon the Qwen2.5 architecture and continues pretrained on a vast corpus of over 5.5 trillion tokens. Through meticulous data cleaning, scalable synthetic data generation, and balanced data mixing, Qwen2.5-Coder demonstrates impressive code generation capabilities while retaining general versatility. The model has been evaluated on a wide range of code-related tasks, achieving state-of-the-art (SOTA) performance across more than 10 benchmarks, including code generation, completion, reasoning, and repair, consistently outperforming larger models of the same model size. We believe that the release of the Qwen2.5-Coder series will not only push the boundaries of research in code intelligence but also, through its permissive licensing, encourage broader adoption by developers in real-world applications.

new Gender Representation and Bias in Indian Civil Service Mock Interviews

Authors: Somonnoy Banerjee, Sujan Dutta, Soumyajit Datta, Ashiqur R. KhudaBukhsh

Abstract: This paper makes three key contributions. First, via a substantial corpus of 51,278 interview questions sourced from 888 YouTube videos of mock interviews of Indian civil service candidates, we demonstrate stark gender bias in the broad nature of questions asked to male and female candidates. Second, our experiments with large language models show a strong presence of gender bias in explanations provided by the LLMs on the gender inference task. Finally, we present a novel dataset of 51,278 interview questions that can inform future social science studies.

cross AIvril: AI-Driven RTL Generation With Verification In-The-Loop

Authors: Mubashir ul Islam, Humza Sami, Pierre-Emmanuel Gaillardon, Valerio Tenace

Abstract: Large Language Models (LLMs) are computational models capable of performing complex natural language processing tasks. Leveraging these capabilities, LLMs hold the potential to transform the entire hardware design stack, with predictions suggesting that front-end and back-end tasks could be fully automated in the near future. Currently, LLMs show great promise in streamlining Register Transfer Level (RTL) generation, enhancing efficiency, and accelerating innovation. However, their probabilistic nature makes them prone to inaccuracies - a significant drawback in RTL design, where reliability and precision are essential. To address these challenges, this paper introduces AIvril, an advanced framework designed to enhance the accuracy and reliability of RTL-aware LLMs. AIvril employs a multi-agent, LLM-agnostic system for automatic syntax correction and functional verification, significantly reducing - and in many cases, completely eliminating - instances of erroneous code generation. Experimental results conducted on the VerilogEval-Human dataset show that our framework improves code quality by nearly 2x when compared to previous works, while achieving an 88.46% success rate in meeting verification objectives. This represents a critical step toward automating and optimizing hardware design workflows, offering a more dependable methodology for AI-driven RTL design.

cross Jailbreaking Large Language Models with Symbolic Mathematics

Authors: Emet Bethany, Mazal Bethany, Juan Arturo Nolazco Flores, Sumit Kumar Jha, Peyman Najafirad

Abstract: Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential vulnerabilities unexplored. This paper introduces MathPrompt, a novel jailbreaking technique that exploits LLMs' advanced capabilities in symbolic mathematics to bypass their safety mechanisms. By encoding harmful natural language prompts into mathematical problems, we demonstrate a critical vulnerability in current AI safety measures. Our experiments across 13 state-of-the-art LLMs reveal an average attack success rate of 73.6\%, highlighting the inability of existing safety training mechanisms to generalize to mathematically encoded inputs. Analysis of embedding vectors shows a substantial semantic shift between original and encoded prompts, helping explain the attack's success. This work emphasizes the importance of a holistic approach to AI safety, calling for expanded red-teaming efforts to develop robust safeguards across all potential input types and their associated risks.

cross Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning

Authors: Ilaria Manco, Justin Salamon, Oriol Nieto

Abstract: Audio-text contrastive models have become a powerful approach in music representation learning. Despite their empirical success, however, little is known about the influence of key design choices on the quality of music-text representations learnt through this framework. In this work, we expose these design choices within the constraints of limited data and computation budgets, and establish a more solid understanding of their impact grounded in empirical observations along three axes: the choice of base encoders, the level of curation in training data, and the use of text augmentation. We find that data curation is the single most important factor for music-text contrastive training in resource-constrained scenarios. Motivated by this insight, we introduce two novel techniques, Augmented View Dropout and TextSwap, which increase the diversity and descriptiveness of text inputs seen in training. Through our experiments we demonstrate that these are effective at boosting performance across different pre-training regimes, model architectures, and downstream data distributions, without incurring higher computational costs or requiring additional training data.

cross Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation

Authors: To Eun Kim, Fernando Diaz

Abstract: Many language models now enhance their responses with retrieval capabilities, leading to the widespread adoption of retrieval-augmented generation (RAG) systems. However, despite retrieval being a core component of RAG, much of the research in this area overlooks the extensive body of work on fair ranking, neglecting the importance of considering all stakeholders involved. This paper presents the first systematic evaluation of RAG systems integrated with fair rankings. We focus specifically on measuring the fair exposure of each relevant item across the rankings utilized by RAG systems (i.e., item-side fairness), aiming to promote equitable growth for relevant item providers. To gain a deep understanding of the relationship between item-fairness, ranking quality, and generation quality in the context of RAG, we analyze nine different RAG systems that incorporate fair rankings across seven distinct datasets. Our findings indicate that RAG systems with fair rankings can maintain a high level of generation quality and, in many cases, even outperform traditional RAG systems, despite the general trend of a tradeoff between ensuring fairness and maintaining system-effectiveness. We believe our insights lay the groundwork for responsible and equitable RAG systems and open new avenues for future research. We publicly release our codebase and dataset at https://github.com/kimdanny/Fair-RAG.

URLs: https://github.com/kimdanny/Fair-RAG.

cross FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement

Authors: Liam Hebert, Marialena Kyriakidi, Hubert Pham, Krishna Sayana, James Pine, Sukhdeep Sodhi, Ambarish Jash

Abstract: Hybrid recommender systems, combining item IDs and textual descriptions, offer potential for improved accuracy. However, previous work has largely focused on smaller datasets and model architectures. This paper introduces Flare (Fusing Language models and collaborative Architectures for Recommender Enhancement), a novel hybrid recommender that integrates a language model (mT5) with a collaborative filtering model (Bert4Rec) using a Perceiver network. This architecture allows Flare to effectively combine collaborative and content information for enhanced recommendations. We conduct a two-stage evaluation, first assessing Flare's performance against established baselines on smaller datasets, where it demonstrates competitive accuracy. Subsequently, we evaluate Flare on a larger, more realistic dataset with a significantly larger item vocabulary, introducing new baselines for this setting. Finally, we showcase Flare's inherent ability to support critiquing, enabling users to provide feedback and refine recommendations. We further leverage critiquing as an evaluation method to assess the model's language understanding and its transferability to the recommendation task.

cross Retrieve, Annotate, Evaluate, Repeat: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation

Authors: Kasra Hosseini, Thomas Kober, Josip Krapac, Roland Vollgraf, Weiwei Cheng, Ana Peleteiro Ramallo

Abstract: Evaluating production-level retrieval systems at scale is a crucial yet challenging task due to the limited availability of a large pool of well-trained human annotators. Large Language Models (LLMs) have the potential to address this scaling issue and offer a viable alternative to humans for the bulk of annotation tasks. In this paper, we propose a framework for assessing the product search engines in a large-scale e-commerce setting, leveraging Multimodal LLMs for (i) generating tailored annotation guidelines for individual queries, and (ii) conducting the subsequent annotation task. Our method, validated through deployment on a large e-commerce platform, demonstrates comparable quality to human annotations, significantly reduces time and cost, facilitates rapid problem discovery, and provides an effective solution for production-level quality control at scale.

cross Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference

Authors: Edresson Casanova, Ryan Langman, Paarth Neekhara, Shehzeen Hussain, Jason Li, Subhankar Ghosh, Ante Juki\'c, Sang-gil Lee

Abstract: Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often operate at high frame rates, resulting in slow training and inference, especially for autoregressive models. To address this challenge, we present the Low Frame-rate Speech Codec (LFSC): a neural audio codec that leverages finite scalar quantization and adversarial training with large speech language models to achieve high-quality audio compression with a 1.89 kbps bitrate and 21.5 frames per second. We demonstrate that our novel codec can make the inference of LLM-based text-to-speech models around three times faster while improving intelligibility and producing quality comparable to previous models.

cross Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Authors: Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, Junyang Lin

Abstract: We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos. We employ a unified paradigm for processing both images and videos, enhancing the model's visual perception capabilities. To explore the potential of large multimodal models, Qwen2-VL investigates the scaling laws for large vision-language models (LVLMs). By scaling both the model size-with versions at 2B, 8B, and 72B parameters-and the amount of training data, the Qwen2-VL Series achieves highly competitive performance. Notably, the Qwen2-VL-72B model achieves results comparable to leading models such as GPT-4o and Claude3.5-Sonnet across various multimodal benchmarks, outperforming other generalist models. Code is available at \url{https://github.com/QwenLM/Qwen2-VL}.

URLs: https://github.com/QwenLM/Qwen2-VL

replace AugTriever: Unsupervised Dense Retrieval by Scalable Data Augmentation

Authors: Rui Meng, Ye Liu, Semih Yavuz, Divyansh Agarwal, Lifu Tu, Ning Yu, Jianguo Zhang, Meghana Bhat, Yingbo Zhou

Abstract: Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-annotated supervision. In this study, we aim to develop unsupervised methods for improving dense retrieval models. We propose two approaches that enable annotation-free and scalable training by creating pseudo querydocument pairs: query extraction and transferred query generation. The query extraction method involves selecting salient spans from the original document to generate pseudo queries. On the other hand, the transferred query generation method utilizes generation models trained for other NLP tasks, such as summarization, to produce pseudo queries. Through extensive experimentation, we demonstrate that models trained using these augmentation methods can achieve comparable, if not better, performance than multiple strong dense baselines. Moreover, combining these strategies leads to further improvements, resulting in superior performance of unsupervised dense retrieval, unsupervised domain adaptation and supervised finetuning, benchmarked on both BEIR and ODQA datasets. Code and datasets are publicly available at https://github.com/salesforce/AugTriever.

URLs: https://github.com/salesforce/AugTriever.

replace Measuring Dimensions of Self-Presentation in Twitter Bios and their Links to Misinformation Sharing

Authors: Navid Madani, Rabiraj Bandyopadhyay, Briony Swire-Thompson, Michael Miller Yoder, Kenneth Joseph

Abstract: Social media platforms provide users with a profile description field, commonly known as a ``bio," where they can present themselves to the world. A growing literature shows that text in these bios can improve our understanding of online self-presentation and behavior, but existing work relies exclusively on keyword-based approaches to do so. We here propose and evaluate a suite of \hl{simple, effective, and theoretically motivated} approaches to embed bios in spaces that capture salient dimensions of social meaning, such as age and partisanship. We \hl{evaluate our methods on four tasks, showing that the strongest one out-performs several practical baselines.} We then show the utility of our method in helping understand associations between self-presentation and the sharing of URLs from low-quality news sites on Twitter\hl{, with a particular focus on explore the interactions between age and partisanship, and exploring the effects of self-presentations of religiosity}. Our work provides new tools to help computational social scientists make use of information in bios, and provides new insights into how misinformation sharing may be perceived on Twitter.

replace PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning

Authors: Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona J. Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren, Yejin Choi

Abstract: Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex and often contextualized situations, e.g. ``scheduling a doctor's appointment without a phone''. While current approaches show encouraging results using large language models (LLMs), they are hindered by drawbacks such as costly API calls and reproducibility issues. In this paper, we advocate planning using smaller language models. We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (constrained) language planning capabilities. More concretely, we develop symbolic procedural knowledge distillation to enhance the commonsense knowledge in small language models and an inference-time algorithm to facilitate more structured and accurate reasoning. In addition, we introduce a new related task, Replanning, that requires a revision of a plan to cope with a constrained situation. In both the planning and replanning settings, we show that orders-of-magnitude smaller models (770M-11B parameters) can compete and often surpass their larger teacher models' capabilities. Finally, we showcase successful application of PlaSma in an embodied environment, VirtualHome.

replace ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction

Authors: Alexander Brinkmann, Roee Shraga, Christian Bizer

Abstract: E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison. However, vendors often provide unstructured product descriptions, necessitating the extraction of attribute-value pairs from these texts. BERT-based extraction methods require large amounts of task-specific training data and struggle with unseen attribute values. This paper explores using large language models (LLMs) as a more training-data efficient and robust alternative. We propose prompt templates for zero-shot and few-shot scenarios, comparing textual and JSON-based target schema representations. Our experiments show that GPT-4 achieves the highest average F1-score of 85% using detailed attribute descriptions and demonstrations. Llama-3-70B performs nearly as well, offering a competitive open-source alternative. GPT-4 surpasses the best PLM baseline by 5% in F1-score. Fine-tuning GPT-3.5 increases the performance to the level of GPT-4 but reduces the model's ability to generalize to unseen attribute values.

replace Fine-grained LLM Agent: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback

Authors: Wenda Xu, Daniel Deutsch, Mara Finkelstein, Juraj Juraska, Biao Zhang, Zhongtao Liu, William Yang Wang, Lei Li, Markus Freitag

Abstract: Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose Fine-grained LLM agent, an inference time optimization method to refine LLM's output. The core idea is to use a learned fine-grained feedback model to pinpoint defects and guide LLM to refine them iteratively. Using original LLM as a proposal of edits, Fine-grained LLM agent searches for defect-less text via simulated annealing, trading off the exploration and exploitation. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. Fine-grained LLM agent consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.

replace ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

Authors: Zhihang Yuan, Yuzhang Shang, Yue Song, Qiang Wu, Yan Yan, Guangyu Sun

Abstract: In this paper, we introduce a new post-training compression paradigm for Large Language Models (LLMs) to facilitate their wider adoption. We delve into LLM weight low-rank factorization, and find that the challenges of this task stem from the outlier phenomenon in the LLM activations and the sensitivity difference among various kinds of layers. To address these issues, we propose a training-free approach called Activation-aware Singular Value Decomposition (ASVD). Specifically, ASVD manages activation outliers by scaling the weight matrix based on the activation distribution, thereby enhancing decomposition accuracy. Additionally, we propose an efficient iterative calibration process to optimize layer-specific decomposition by addressing the varying sensitivity of different LLM layers. ASVD can compress a network by 10-20%, without compromising the performance of LLMs. Based on the success of the low-rank decomposition of projection matrices in the self-attention module, we further introduce ASVD to compress the KV cache. By reducing the channel dimension of KV activations, memory requirements for KV cache can be largely reduced. Thanks to the 50-75% reduction in the rank of the KV projection matrices, ASVD can further achieve 50% KV cache reductions without performance drop in a training-free manner.

replace Natural Language Processing for Dialects of a Language: A Survey

Authors: Aditya Joshi, Raj Dabre, Diptesh Kanojia, Zhuang Li, Haolan Zhan, Gholamreza Haffari, Doris Dippold

Abstract: State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dialect classification, sentiment analysis, parsing, and NLU benchmarks) and natural language generation (NLG) (for summarisation, machine translation, and dialogue systems). The survey is also broad in its coverage of languages which include English, Arabic, German among others. We observe that past work in NLP concerning dialects goes deeper than mere dialect classification, and . This includes early approaches that used sentence transduction that lead to the recent approaches that integrate hypernetworks into LoRA. We expect that this survey will be useful to NLP researchers interested in building equitable language technologies by rethinking LLM benchmarks and model architectures.

replace MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL

Authors: Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, Wanxiang Che

Abstract: The open-domain text-to-SQL task aims to retrieve question-relevant tables from massive databases and generate SQL. However, the performance of current methods is constrained by single-hop retrieval, and existing multi-hop retrieval of open-domain question answering is not directly applicable due to the tendency to retrieve tables similar to the retrieved ones but irrelevant to the question. Since the questions in text-to-SQL usually contain all required information, while previous multi-hop retrieval supplements the questions with retrieved documents. Therefore, we propose the multi-hop table retrieval with removal (MURRE), which removes previously retrieved information from the question to guide the retriever towards unretrieved relevant tables. Our experiments on two open-domain text-to-SQL datasets demonstrate an average improvement of 5.7% over the previous state-of-the-art results.

replace A Hybrid Transformer and Attention Based Recurrent Neural Network for Robust and Interpretable Sentiment Analysis of Tweets

Authors: Md Abrar Jahin, Md Sakib Hossain Shovon, M. F. Mridha, Md Rashedul Islam, Yutaka Watanobe

Abstract: Sentiment analysis is crucial for understanding public opinion and consumer behavior. Existing models face challenges with linguistic diversity, generalizability, and explainability. We propose TRABSA, a hybrid framework integrating transformer-based architectures, attention mechanisms, and BiLSTM networks to address this. Leveraging RoBERTa-trained on 124M tweets, we bridge gaps in sentiment analysis benchmarks, ensuring state-of-the-art accuracy. Augmenting datasets with tweets from 32 countries and US states, we compare six word-embedding techniques and three lexicon-based labeling techniques, selecting the best for optimal sentiment analysis. TRABSA outperforms traditional ML and deep learning models with 94% accuracy and significant precision, recall, and F1-score gains. Evaluation across diverse datasets demonstrates consistent superiority and generalizability. SHAP and LIME analyses enhance interpretability, improving confidence in predictions. Our study facilitates pandemic resource management, aiding resource planning, policy formation, and vaccination tactics.

replace Prior Constraints-based Reward Model Training for Aligning Large Language Models

Authors: Hang Zhou, Chenglong Wang, Yimin Hu, Tong Xiao, Chunliang Zhang, Jingbo Zhu

Abstract: Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled scaling of reward scores during reinforcement learning due to the lack of constraints while training the reward model.This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem. PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins. We comprehensively evaluate PCRM by examining its rank correlation with human preferences and its effectiveness in aligning LLMs via RL. Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling. As another bonus, our method is easily integrated into arbitrary rank-based alignment methods, such as direct preference optimization, and can yield consistent improvement.

replace Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models

Authors: Taiqiang Wu, Chaofan Tao, Jiahao Wang, Runming Yang, Zhe Zhao, Ngai Wong

Abstract: Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over the mean-seeking forward Kullback-Leibler (FKL) divergence, this study empirically and theoretically demonstrates that neither mode-seeking nor mean-seeking properties manifest in KD for LLMs. Instead, RKL and FKL are found to share the same optimization objective and both converge after a sufficient number of epochs. However, due to practical constraints, LLMs are seldom trained for such an extensive number of epochs. Meanwhile, we further find that RKL focuses on the tail part of the distributions, while FKL focuses on the head part at the beginning epochs. Consequently, we propose a simple yet effective Adaptive Kullback-Leiber (AKL) divergence method, which adaptively allocates weights to combine FKL and RKL. Metric-based and GPT-4-based evaluations demonstrate that the proposed AKL outperforms the baselines across various tasks and improves the diversity and quality of generated responses.

replace Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations

Authors: Xiao Zhang, Gosse Bouma, Johan Bos

Abstract: Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural "taxonomical" semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts. This finding is encouraging for research in computational semantics that aims to combine data-driven distributional meanings with knowledge-based symbolic representations.

replace A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text

Authors: Jeremie Pantin, Christophe Marsala

Abstract: Anomaly detection (AD) is a fast growing and popular domain among established applications like vision and time series. We observe a rich literature for these applications, but anomaly detection in text is only starting to blossom. Recently, self-supervised methods with self-attention mechanism have been the most popular choice. While recent works have proposed a working ground for building and benchmarking state of the art approaches, we propose two principal contributions in this paper: contextual anomaly contamination and a novel ensemble-based approach. Our method, Textual Anomaly Contamination (TAC), allows to contaminate inlier classes with either independent or contextual anomalies. In the literature, it appears that this distinction is not performed. For finding contextual anomalies, we propose RoSAE, a Robust Subspace Local Recovery Autoencoder Ensemble. All autoencoders of the ensemble present a different latent representation through local manifold learning. Benchmark shows that our approach outperforms recent works on both independent and contextual anomalies, while being more robust. We also provide 8 dataset comparison instead of only relying to Reuters and 20 Newsgroups corpora.

replace Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation

Authors: Javad Pourmostafa Roshan Sharami, Dimitar Shterionov, Pieter Spronck

Abstract: The quality of output from large language models (LLMs), particularly in machine translation (MT), is closely tied to the quality of in-context examples (ICEs) provided along with the query, i.e., the text to translate. The effectiveness of these ICEs is influenced by various factors, such as the domain of the source text, the order in which the ICEs are presented, the number of these examples, and the prompt templates used. Naturally, selecting the most impactful ICEs depends on understanding how these affect the resulting translation quality, which ultimately relies on translation references or human judgment. This paper presents a novel methodology for in-context learning (ICL) that relies on a search algorithm guided by domain-specific quality estimation (QE). Leveraging the XGLM model, our methodology estimates the resulting translation quality without the need for translation references, selecting effective ICEs for MT to maximize translation quality. Our results demonstrate significant improvements over existing ICL methods and higher translation performance compared to fine-tuning a pre-trained language model (PLM), specifically mBART-50.

replace MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning

Authors: Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen

Abstract: Efficient finetuning of large language models (LLMs) aims to adapt the LLMs with reduced computational and memory cost. Previous LoRA-based approaches initialize the low-rank matrices with Gaussian distribution and zero values while keeping the original weight matrices frozen. However, the trainable model parameters optimized in an unguided subspace might interfere with the well-learned subspace of the pretrained weight matrices. In this paper, we propose MiLoRA, a simple yet effective LLM finetuning approach that only updates the minor singular components of the weight matrix while keeping the principal singular components frozen. It is observed that the minor matrix corresponds to the noisy or long-tail information, while the principal matrix contains important knowledge. The MiLoRA initializes the low-rank matrices within a subspace that is orthogonal to the principal matrix, thus the pretrained knowledge is expected to be well preserved. During finetuning, MiLoRA makes the most use of the less-optimized subspace for learning the labeled dataset. Extensive experiments on commonsense reasoning, math reasoning, instruction following and visual instruction following benchmarks present the superior performance of our method.

replace Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings

Authors: Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

Abstract: Cosine similarity is widely used to measure the similarity between two embeddings, while interpretations based on angle and correlation coefficient are common. In this study, we focus on the interpretable axes of embeddings transformed by Independent Component Analysis (ICA), and propose a novel interpretation of cosine similarity as the sum of semantic similarities over axes. The normalized ICA-transformed embeddings exhibit sparsity, enhancing the interpretability of each axis, and the semantic similarity defined by the product of the components represents the shared meaning between the two embeddings along each axis. The effectiveness of this approach is demonstrated through intuitive numerical examples and thorough numerical experiments. By deriving the probability distributions that govern each component and the product of components, we propose a method for selecting statistically significant axes.

replace Integrating Knowledge Retrieval and Large Language Models for Clinical Report Correction

Authors: Jinge Wu, Zhaolong Wu, Ruizhe Li, Abul Hasan, Yunsoo Kim, Jason P. Y. Cheung, Teng Zhang, Honghan Wu

Abstract: This study proposes an approach for error correction in radiology reports, leveraging large language models (LLMs) and retrieval-augmented generation (RAG) techniques. The proposed framework employs a novel internal+external retrieval mechanism to extract relevant medical entities and relations from the report of interest and an external knowledge source. A three-stage inference process is introduced, decomposing the task into error detection, localization, and correction subtasks, which enhances the explainability and performance of the system. The effectiveness of the approach is evaluated using a benchmark dataset created by corrupting real-world radiology reports with realistic errors, guided by domain experts. Experimental results demonstrate the benefits of the proposed methods, with the combination of internal and external retrieval significantly improving the accuracy of error detection, localization, and correction across various state-of-the-art LLMs. The findings contribute to the development of more robust and reliable error correction systems for clinical documentation.

replace Unmasking the Imposters: How Censorship and Domain Adaptation Affect the Detection of Machine-Generated Tweets

Authors: Bryan E. Tuck, Rakesh M. Verma

Abstract: The rapid development of large language models (LLMs) has significantly improved the generation of fluent and convincing text, raising concerns about their potential misuse on social media platforms. We present a comprehensive methodology for creating nine Twitter datasets to examine the generative capabilities of four prominent LLMs: Llama 3, Mistral, Qwen2, and GPT4o. These datasets encompass four censored and five uncensored model configurations, including 7B and 8B parameter base-instruction models of the three open-source LLMs. Additionally, we perform a data quality analysis to assess the characteristics of textual outputs from human, "censored," and "uncensored" models, employing semantic meaning, lexical richness, structural patterns, content characteristics, and detector performance metrics to identify differences and similarities. Our evaluation demonstrates that "uncensored" models significantly undermine the effectiveness of automated detection methods. This study addresses a critical gap by exploring smaller open-source models and the ramifications of "uncensoring," providing valuable insights into how domain adaptation and content moderation strategies influence both the detectability and structural characteristics of machine-generated text.

replace Show Less, Instruct More: Enriching Prompts with Definitions and Guidelines for Zero-Shot NER

Authors: Andrew Zamai, Andrea Zugarini, Leonardo Rigutini, Marco Ernandes, Marco Maggini

Abstract: Recently, several specialized instruction-tuned Large Language Models (LLMs) for Named Entity Recognition (NER) have emerged. Compared to traditional NER approaches, these models have demonstrated strong generalization capabilities. Existing LLMs primarily focus on addressing zero-shot NER on Out-of-Domain inputs, while fine-tuning on an extensive number of entity classes that often highly or completely overlap with test sets. In this work instead, we propose SLIMER, an approach designed to tackle never-seen-before entity tags by instructing the model on fewer examples, and by leveraging a prompt enriched with definition and guidelines. Experiments demonstrate that definition and guidelines yield better performance, faster and more robust learning, particularly when labelling unseen named entities. Furthermore, SLIMER performs comparably to state-of-the-art approaches in out-of-domain zero-shot NER, while being trained in a more fair, though certainly more challenging, setting.

replace Conversational Query Reformulation with the Guidance of Retrieved Documents

Authors: Jeonghyun Park, Hwanhee Lee

Abstract: Conversational search seeks to retrieve relevant passages for the given questions in conversational question answering. Conversational Query Reformulation (CQR) improves conversational search by refining the original queries into de-contextualized forms to resolve the issues in the original queries, such as omissions and coreferences. Previous CQR methods focus on imitating human written queries which may not always yield meaningful search results for the retriever. In this paper, we introduce GuideCQR, a framework that refines queries for CQR by leveraging key infFormation from the initially retrieved documents. Specifically, GuideCQR extracts keywords and generates expected answers from the retrieved documents, then unifies them with the queries after filtering to add useful information that enhances the search process. Experimental results demonstrate that our proposed method achieves state-of-the-art performance across multiple datasets, outperforming previous CQR methods. Additionally, we show that GuideCQR can get additional performance gains in conversational search using various types of queries, even for queries written by humans.

replace Internal Consistency and Self-Feedback in Large Language Models: A Survey

Authors: Xun Liang, Shichao Song, Zifan Zheng, Hanyu Wang, Qingchen Yu, Xunkai Li, Rong-Hua Li, Yi Wang, Zhonghao Wang, Feiyu Xiong, Zhiyu Li

Abstract: Large language models (LLMs) often exhibit deficient reasoning or generate hallucinations. To address these, studies prefixed with "Self-" such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a commonality: involving LLMs evaluating and updating themselves. Nonetheless, these efforts lack a unified perspective on summarization, as existing surveys predominantly focus on categorization. In this paper, we use a unified perspective of internal consistency, offering explanations for reasoning deficiencies and hallucinations. Internal consistency refers to the consistency in expressions among LLMs' latent, decoding, or response layers based on sampling methodologies. Then, we introduce an effective theoretical framework capable of mining internal consistency, named Self-Feedback. This framework consists of two modules: Self-Evaluation and Self-Update. The former captures internal consistency signals, while the latter leverages the signals to enhance either the model's response or the model itself. This framework has been employed in numerous studies. We systematically classify these studies by tasks and lines of work; summarize relevant evaluation methods and benchmarks; and delve into the concern, "Does Self-Feedback Really Work?" We also propose several critical viewpoints, including the "Hourglass Evolution of Internal Consistency", "Consistency Is (Almost) Correctness" hypothesis, and "The Paradox of Latent and Explicit Reasoning". The relevant resources are open-sourced at https://github.com/IAAR-Shanghai/ICSFSurvey.

URLs: https://github.com/IAAR-Shanghai/ICSFSurvey.

replace Unlock the Power of Frozen LLMs in Knowledge Graph Completion

Authors: Bo Xue, Yi Xu, Yunchong Song, Yiming Pang, Yuyang Ren, Jiaxin Ding, Luoyi Fu, Xinbing Wang

Abstract: Traditional knowledge graph completion (KGC) methods rely solely on structural information, struggling with the inherent sparsity of knowledge graphs (KGs). Large Language Models (LLMs) learn extensive knowledge from large corpora with powerful context modeling, making them promising for mitigating the limitations of previous methods. Directly fine-tuning LLMs offers great capability but comes at the cost of huge time and memory consumption, while utilizing frozen LLMs yields suboptimal results.In this work, we aim to leverage LLMs for KGC effectively and efficiently. We capture the context-aware hidden states of knowledge triples by employing prompts to stimulate the intermediate layers of LLMs. We then train a data-efficient classifier on these hidden states to harness the inherent capabilities of frozen LLMs in KGC. Additionally, to reduce ambiguity and enrich knowledge representation, we generate detailed entity descriptions through subgraph sampling on KGs. Extensive experiments on standard benchmarks demonstrate the efficiency and effectiveness of our approach. We outperform traditional KGC methods across most datasets and, notably, achieve classification performance comparable to fine-tuned LLMs while enhancing GPU memory efficiency by $188\times$ and accelerating training and inference by $13.48\times$.

replace Adversarial Attack for Explanation Robustness of Rationalization Models

Authors: Yuankai Zhang, Lingxiao Kong, Haozhao Wang, Ruixuan Li, Jun Wang, Yuhua Li, Wei Liu

Abstract: Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of previous studies mainly focus on improving the quality of the rationale, ignoring its robustness to malicious attack. Specifically, whether the rationalization models can still generate high-quality rationale under the adversarial attack remains unknown. To explore this, this paper proposes UAT2E, which aims to undermine the explainability of rationalization models without altering their predictions, thereby eliciting distrust in these models from human users. UAT2E employs the gradient-based search on triggers and then inserts them into the original input to conduct both the non-target and target attack. Experimental results on five datasets reveal the vulnerability of rationalization models in terms of explanation, where they tend to select more meaningless tokens under attacks. Based on this, we make a series of recommendations for improving rationalization models in terms of explanation.

replace CoT Rerailer: Enhancing the Reliability of Large Language Models in Complex Reasoning Tasks through Error Detection and Correction

Authors: Guangya Wan, Yuqi Wu, Jie Chen, Sheng Li

Abstract: Chain-of-Thought (CoT) prompting enhances Large Language Models (LLMs) complex reasoning abilities by generating intermediate steps. However, these steps can introduce hallucinations and accumulate errors. We propose the CoT Rerailer to address these challenges, employing self-consistency and multi-agent debate systems to identify and rectify errors in the reasoning process. The CoT Rerailer first selects the most logically correct Reasoning Path (RP) using consistency checks and critical evaluation by automated agents. It then engages a multi-agent debate system to propose and validate corrections to ensure the generation of an error-free intermediate logical path. The corrected steps are then used to generate a revised reasoning chain to further reduce hallucinations and enhance answer quality. We demonstrate the effectiveness of our approach across diverse question-answering datasets in various knowledge domains. The CoT Rerailer enhances the reliability of LLM-generated reasoning, contributing to more trustworthy AI driven decision-making processes.

replace MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs

Authors: Saeid Asgari Taghanaki, Aliasgahr Khani, Amir Khasahmadi

Abstract: Existing benchmarks for large language models (LLMs) increasingly struggle to differentiate between top-performing models, underscoring the need for more challenging evaluation frameworks. We introduce MMLU-Pro+, an enhanced benchmark building upon MMLU-Pro to assess shortcut learning and higher-order reasoning in LLMs. By incorporating questions with multiple correct answers across diverse domains, MMLU-Pro+ tests LLMs' ability to engage in complex reasoning and resist simplistic problem-solving strategies. Our results show that MMLU-Pro+ maintains MMLU-Pro's difficulty while providing a more rigorous test of model discrimination, particularly in multi-correct answer scenarios. We introduce novel metrics like shortcut selection ratio and correct pair identification ratio, offering deeper insights into model behavior and anchoring bias. Evaluations of six state-of-the-art LLMs reveal significant performance gaps, highlighting variations in reasoning abilities and bias susceptibility. We release the dataset and evaluation codes at \url{https://github.com/asgsaeid/mmlu-pro-plus}.

URLs: https://github.com/asgsaeid/mmlu-pro-plus

replace Leveraging Large Language Models for Solving Rare MIP Challenges

Authors: Teng Wang, Wing-Yin Yu, Ruifeng She, Wenhan Yang, Taijie Chen, Jianping Zhang

Abstract: Mixed Integer Programming (MIP) has been extensively applied in areas requiring mathematical solvers to address complex instances within tight time constraints. However, as the problem scale increases, the complexity of model formulation and finding feasible solutions escalates significantly. In contrast, the model-building cost for end-to-end models, such as large language models (LLMs), remains largely unaffected by problem scale due to their pattern recognition capabilities. While LLMs, like GPT-4, without fine-tuning, can handle some traditional medium-scale MIP problems, they struggle with uncommon or highly specialized MIP scenarios. Fine-tuning LLMs can yield some feasible solutions for medium-scale MIP instances, but these models typically fail to explore diverse solutions when constrained by a low and constant temperature, limiting their performance. In this paper, we propose and evaluate a recursively dynamic temperature method integrated with a chain-of-thought approach. Our findings show that starting with a high temperature and gradually lowering it leads to better feasible solutions compared to other dynamic temperature strategies. Additionally, by comparing results generated by the LLM with those from Gurobi, we demonstrate that the LLM can produce solutions that complement traditional solvers by accelerating the pruning process and improving overall efficiency.

replace Towards Building a Robust Knowledge Intensive Question Answering Model with Large Language Models

Authors: Xingyun Hong, Yan Shao, Zhilin Wang, Manni Duan, Jin Xiongnan

Abstract: The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and errors in retrieved information poses challenges to the robustness of LLMs. In this work, to evaluate the model's performance under multiple interferences, we first construct a dataset based on machine reading comprehension datasets simulating various scenarios, including critical information absence, noise, and conflicts. To address the issue of model accuracy decline caused by noisy external information, we propose a data augmentation-based fine-tuning method to enhance LLM's robustness against noise. Additionally, contrastive learning approach is utilized to preserve the model's discrimination capability of external information. We have conducted experiments on both existing LLMs and our approach, the results are evaluated by GPT-4, which indicates that our proposed methods improve model robustness while strengthening the model's discrimination capability.

replace Autoregressive + Chain of Thought $\simeq$ Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer

Authors: Xiang Zhang, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan

Abstract: The Transformer architecture excels in a variety of language modeling tasks, outperforming traditional neural architectures such as RNN and LSTM. This is partially due to its elimination of recurrent connections, which allows for parallel training and a smoother flow of gradients. However, this move away from recurrent structures places the Transformer model at the lower end of Chomsky's computational hierarchy, imposing limitations on its computational abilities. Consequently, even advanced Transformer-based models face considerable difficulties in tasks like counting, string reversal, and multiplication. These tasks, though seemingly elementary, require a level of computational complexity that exceeds the capabilities of the Transformer architecture. Concurrently, the emergence of ``Chain of Thought" (CoT) prompting has enabled Transformer-based language models to tackle tasks that were previously impossible or poorly executed. In this work, we thoroughly investigate the influence of recurrent structures in neural models on their reasoning abilities and computability, contrasting the role autoregression plays in the neural models' computational power. We then shed light on how the CoT approach can mimic recurrent computation and act as a bridge between autoregression and recurrence in the context of language models. It is this approximated recurrence that notably improves the model's performance and computational capacity. Moreover, we revisit recent recurrent-based Transformer model designs, focusing on their computational abilities through our proposed concept of ``recurrence-completeness" and identify key theoretical limitations in models like Linear Transformer and RWKV. Through this, we aim to provide insight into the neural model architectures and prompt better model design.

replace NovAScore: A New Automated Metric for Evaluating Document Level Novelty

Authors: Lin Ai, Ziwei Gong, Harshsaiprasad Deshpande, Alexander Johnson, Emmy Phung, Ahmad Emami, Julia Hirschberg

Abstract: The rapid expansion of online content has intensified the issue of information redundancy, underscoring the need for solutions that can identify genuinely new information. Despite this challenge, the research community has seen a decline in focus on novelty detection, particularly with the rise of large language models (LLMs). Additionally, previous approaches have relied heavily on human annotation, which is time-consuming, costly, and particularly challenging when annotators must compare a target document against a vast number of historical documents. In this work, we introduce NovAScore (Novelty Evaluation in Atomicity Score), an automated metric for evaluating document-level novelty. NovAScore aggregates the novelty and salience scores of atomic information, providing high interpretability and a detailed analysis of a document's novelty. With its dynamic weight adjustment scheme, NovAScore offers enhanced flexibility and an additional dimension to assess both the novelty level and the importance of information within a document. Our experiments show that NovAScore strongly correlates with human judgments of novelty, achieving a 0.626 Point-Biserial correlation on the TAP-DLND 1.0 dataset and a 0.920 Pearson correlation on an internal human-annotated dataset.

replace Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports

Authors: Mohamed Sobhi Jabal, Pranav Warman, Jikai Zhang, Kartikeye Gupta, Ayush Jain, Maciej Mazurowski, Walter Wiggins, Kirti Magudia, Evan Calabrese

Abstract: Purpose: To develop and evaluate an automated system for extracting structured clinical information from unstructured radiology and pathology reports using open-weights large language models (LMs) and retrieval augmented generation (RAG), and to assess the effects of model configuration variables on extraction performance. Methods and Materials: The study utilized two datasets: 7,294 radiology reports annotated for Brain Tumor Reporting and Data System (BT-RADS) scores and 2,154 pathology reports annotated for isocitrate dehydrogenase (IDH) mutation status. An automated pipeline was developed to benchmark the performance of various LMs and RAG configurations. The impact of model size, quantization, prompting strategies, output formatting, and inference parameters was systematically evaluated. Results: The best performing models achieved over 98% accuracy in extracting BT-RADS scores from radiology reports and over 90% for IDH mutation status extraction from pathology reports. The top model being medical fine-tuned llama3. Larger, newer, and domain fine-tuned models consistently outperformed older and smaller models. Model quantization had minimal impact on performance. Few-shot prompting significantly improved accuracy. RAG improved performance for complex pathology reports but not for shorter radiology reports. Conclusions: Open LMs demonstrate significant potential for automated extraction of structured clinical data from unstructured clinical reports with local privacy-preserving application. Careful model selection, prompt engineering, and semi-automated optimization using annotated data are critical for optimal performance. These approaches could be reliable enough for practical use in research workflows, highlighting the potential for human-machine collaboration in healthcare data extraction.

replace Exploring Fine-tuned Generative Models for Keyphrase Selection: A Case Study for Russian

Authors: Anna Glazkova, Dmitry Morozov

Abstract: Keyphrase selection plays a pivotal role within the domain of scholarly texts, facilitating efficient information retrieval, summarization, and indexing. In this work, we explored how to apply fine-tuned generative transformer-based models to the specific task of keyphrase selection within Russian scientific texts. We experimented with four distinct generative models, such as ruT5, ruGPT, mT5, and mBART, and evaluated their performance in both in-domain and cross-domain settings. The experiments were conducted on the texts of Russian scientific abstracts from four domains: mathematics & computer science, history, medicine, and linguistics. The use of generative models, namely mBART, led to gains in in-domain performance (up to 4.9% in BERTScore, 9.0% in ROUGE-1, and 12.2% in F1-score) over three keyphrase extraction baselines for the Russian language. Although the results for cross-domain usage were significantly lower, they still demonstrated the capability to surpass baseline performances in several cases, underscoring the promising potential for further exploration and refinement in this research field.

replace Visualizing Temporal Topic Embeddings with a Compass

Authors: Daniel Palamarchuk, Lemara Williams, Brian Mayer, Thomas Danielson, Rebecca Faust, Larry Deschaine, Chris North

Abstract: Dynamic topic modeling is useful at discovering the development and change in latent topics over time. However, present methodology relies on algorithms that separate document and word representations. This prevents the creation of a meaningful embedding space where changes in word usage and documents can be directly analyzed in a temporal context. This paper proposes an expansion of the compass-aligned temporal Word2Vec methodology into dynamic topic modeling. Such a method allows for the direct comparison of word and document embeddings across time in dynamic topics. This enables the creation of visualizations that incorporate temporal word embeddings within the context of documents into topic visualizations. In experiments against the current state-of-the-art, our proposed method demonstrates overall competitive performance in topic relevancy and diversity across temporal datasets of varying size. Simultaneously, it provides insightful visualizations focused on temporal word embeddings while maintaining the insights provided by global topic evolution, advancing our understanding of how topics evolve over time.

replace Propulsion: Steering LLM with Tiny Fine-Tuning

Authors: Md Kowsher, Nusrat Jahan Prottasha, Prakash Bhat

Abstract: The rapid advancements in Large Language Models (LLMs) have revolutionized natural language processing (NLP) and related fields. However, fine-tuning these models for specific tasks remains computationally expensive and risks degrading pre-learned features. To address these challenges, we propose Propulsion, a novel parameter efficient fine-tuning (PEFT) method designed to optimize task-specific performance while drastically reducing computational overhead. Inspired by the concept of controlled adjustments in physical motion, Propulsion selectively re-scales specific dimensions of a pre-trained model, guiding output predictions toward task objectives without modifying the model's parameters. By introducing lightweight, trainable Propulsion parameters at the pre-trained layer, we minimize the number of parameters updated during fine-tuning, preventing overfitting or overwriting of existing knowledge. Our theoretical analysis, supported by Neural Tangent Kernel (NTK) theory, shows that Propulsion approximates the performance of full fine-tuning with far fewer trainable parameters. Empirically, Propulsion reduces the parameter count from 355.3 million to just 0.086 million, achieving over a 10x reduction compared to standard approaches like LoRA while maintaining competitive performance across benchmarks.

replace Contextual Breach: Assessing the Robustness of Transformer-based QA Models

Authors: Asir Saadat, Nahian Ibn Asad, Md Farhan Ishmam

Abstract: Contextual question-answering models are susceptible to adversarial perturbations to input context, commonly observed in real-world scenarios. These adversarial noises are designed to degrade the performance of the model by distorting the textual input. We introduce a unique dataset that incorporates seven distinct types of adversarial noise into the context, each applied at five different intensity levels on the SQuAD dataset. To quantify the robustness, we utilize robustness metrics providing a standardized measure for assessing model performance across varying noise types and levels. Experiments on transformer-based question-answering models reveal robustness vulnerabilities and important insights into the model's performance in realistic textual input.

replace GEIC: Universal and Multilingual Named Entity Recognition with Large Language Models

Authors: Hanjun Luo, Yingbin Jin, Xuecheng Liu, Tong Shang, Ruizhe Chen, Zuozhu Liu

Abstract: Large Language Models (LLMs) have supplanted traditional methods in numerous natural language processing tasks. Nonetheless, in Named Entity Recognition (NER), existing LLM-based methods underperform compared to baselines and require significantly more computational resources, limiting their application. In this paper, we introduce the task of generation-based extraction and in-context classification (GEIC), designed to leverage LLMs' prior knowledge and self-attention mechanisms for NER tasks. We then propose CascadeNER, a universal and multilingual GEIC framework for few-shot and zero-shot NER. CascadeNER employs model cascading to utilize two small-parameter LLMs to extract and classify independently, reducing resource consumption while enhancing accuracy. We also introduce AnythingNER, the first NER dataset specifically designed for LLMs, including 8 languages, 155 entity types and a novel dynamic categorization system. Experiments show that CascadeNER achieves state-of-the-art performance on low-resource and fine-grained scenarios, including CrossNER and FewNERD. Our work is openly accessible.

replace Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming

Authors: Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

Abstract: While there has been a lot of research recently on robots in household environments, at the present time, most robots in existence can be found on shop floors, and most interactions between humans and robots happen there. ``Collaborative robots'' (cobots) designed to work alongside humans on assembly lines traditionally require expert programming, limiting ability to make changes, or manual guidance, limiting expressivity of the resulting programs. To address these limitations, we explore using Large Language Models (LLMs), and in particular, their abilities of doing in-context learning, for conversational code generation. As a first step, we define RATS, the ``Repetitive Assembly Task'', a 2D building task designed to lay the foundation for simulating industry assembly scenarios. In this task, a `programmer' instructs a cobot, using natural language, on how a certain assembly is to be built; that is, the programmer induces a program, through natural language. We create a dataset that pairs target structures with various example instructions (human-authored, template-based, and model-generated) and example code. With this, we systematically evaluate the capabilities of state-of-the-art LLMs for synthesising this kind of code, given in-context examples. Evaluating in a simulated environment, we find that LLMs are capable of generating accurate `first order code' (instruction sequences), but have problems producing `higher-order code' (abstractions such as functions, or use of loops).

replace The Art of Storytelling: Multi-Agent Generative AI for Dynamic Multimodal Narratives

Authors: Samee Arif, Taimoor Arif, Aamina Jamal Khan, Muhammad Saad Haroon, Agha Ali Raza, Awais Athar

Abstract: This paper introduces the concept of an education tool that utilizes Generative Artificial Intelligence (GenAI) to enhance storytelling for children. The system combines GenAI-driven narrative co-creation, text-to-speech conversion, and text-to-video generation to produce an engaging experience for learners. We describe the co-creation process, the adaptation of narratives into spoken words using text-to-speech models, and the transformation of these narratives into contextually relevant visuals through text-to-video technology. Our evaluation covers the linguistics of the generated stories, the text-to-speech conversion quality, and the accuracy of the generated visuals.

replace LOLA -- An Open-Source Massively Multilingual Large Language Model

Authors: Nikit Srivastava, Denis Kuchelev, Tatiana Moteu, Kshitij Shetty, Michael R\"oder, Diego Moussallem, Hamada Zahera, Axel-Cyrille Ngonga Ngomo

Abstract: This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of harnessing linguistic diversity while maintaining efficiency and avoiding the common pitfalls of multilinguality. Our analysis of the evaluation results shows competitive performance in natural language generation and understanding tasks. Additionally, we demonstrate how the learned expert-routing mechanism exploits implicit phylogenetic linguistic patterns to potentially alleviate the curse of multilinguality. We provide an in-depth look at the training process, an analysis of the datasets, and a balanced exploration of the model's strengths and limitations. As an open-source model, LOLA promotes reproducibility and serves as a robust foundation for future research. Our findings enable the development of compute-efficient multilingual models with strong, scalable performance across languages.

replace Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

Authors: Xinyue Fang, Zhen Huang, Zhiliang Tian, Minghui Fang, Ziyi Pan, Quntian Fang, Zhihua Wen, Hengyue Pan, Dongsheng Li

Abstract: LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections for text generation with open-ended answers are more challenging. Some researchers use external knowledge to detect hallucinations in generated texts, but external resources for specific scenarios are hard to access. Recent studies on detecting hallucinations in long text without external resources conduct consistency comparison among multiple sampled outputs. To handle long texts, researchers split long texts into multiple facts and individually compare the consistency of each pairs of facts. However, these methods (1) hardly achieve alignment among multiple facts; (2) overlook dependencies between multiple contextual facts. In this paper, we propose a graph-based context-aware (GCA) hallucination detection for text generations, which aligns knowledge facts and considers the dependencies between contextual knowledge triples in consistency comparison. Particularly, to align multiple facts, we conduct a triple-oriented response segmentation to extract multiple knowledge triples. To model dependencies among contextual knowledge triple (facts), we construct contextual triple into a graph and enhance triples' interactions via message passing and aggregating via RGCN. To avoid the omission of knowledge triples in long text, we conduct a LLM-based reverse verification via reconstructing the knowledge triples. Experiments show that our model enhances hallucination detection and excels all baselines.

replace-cross On the Creativity of Large Language Models

Authors: Giorgio Franceschelli, Mirco Musolesi

Abstract: Large Language Models (LLMs) are revolutionizing several areas of Artificial Intelligence. One of the most remarkable applications is creative writing, e.g., poetry or storytelling: the generated outputs are often of astonishing quality. However, a natural question arises: can LLMs be really considered creative? In this article, we first analyze the development of LLMs under the lens of creativity theories, investigating the key open questions and challenges. In particular, we focus our discussion on the dimensions of value, novelty, and surprise as proposed by Margaret Boden in her work. Then, we consider different classic perspectives, namely product, process, press, and person. We discuss a set of ``easy'' and ``hard'' problems in machine creativity, presenting them in relation to LLMs. Finally, we examine the societal impact of these technologies with a particular focus on the creative industries, analyzing the opportunities offered, the challenges arising from them, and the potential associated risks, from both legal and ethical points of view.

replace-cross Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Authors: Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons

Abstract: Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at inference time, and introduce the general Behaviour Matching algorithm for training image hijacks. From this, we derive the Prompt Matching method, allowing us to train hijacks matching the behaviour of an arbitrary user-defined text prompt (e.g. 'the Eiffel Tower is now located in Rome') using a generic, off-the-shelf dataset unrelated to our choice of prompt. We use Behaviour Matching to craft hijacks for four types of attack, forcing VLMs to generate outputs of the adversary's choice, leak information from their context window, override their safety training, and believe false statements. We study these attacks against LLaVA, a state-of-the-art VLM based on CLIP and LLaMA-2, and find that all attack types achieve a success rate of over 80%. Moreover, our attacks are automated and require only small image perturbations.

replace-cross LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education

Authors: Unggi Lee, Minji Jeon, Yunseo Lee, Gyuri Byun, Yoorim Son, Jaeyoon Shin, Hongkyu Ko, Hyeoncheol Kim

Abstract: Despite the development of various AI systems to support learning in various domains, AI assistance for art appreciation education has not been extensively explored. Art appreciation, often perceived as an unfamiliar and challenging endeavor for most students, can be more accessible with a generative AI enabled conversation partner that provides tailored questions and encourages the audience to deeply appreciate artwork. This study explores the application of multimodal large language models (MLLMs) in art appreciation education, with a focus on developing LLaVA-Docent, a model designed to serve as a personal tutor for art appreciation. Our approach involved design and development research, focusing on iterative enhancement to design and develop the application to produce a functional MLLM-enabled chatbot along with a data design framework for art appreciation education. To that end, we established a virtual dialogue dataset that was generated by GPT-4, which was instrumental in training our MLLM, LLaVA-Docent. The performance of LLaVA-Docent was evaluated by benchmarking it against alternative settings and revealed its distinct strengths and weaknesses. Our findings highlight the efficacy of the MMLM-based personalized art appreciation chatbot and demonstrate its applicability for a novel approach in which art appreciation is taught and experienced.

replace-cross Creative Beam Search: LLM-as-a-Judge For Improving Response Generation

Authors: Giorgio Franceschelli, Mirco Musolesi

Abstract: Large language models are revolutionizing several areas, including artificial creativity. However, the process of generation in machines profoundly diverges from that observed in humans. In particular, machine generation is characterized by a lack of intentionality and an underlying creative process. We propose a method called Creative Beam Search that uses Diverse Beam Search and LLM-as-a-Judge to perform response generation and response validation. The results of a qualitative experiment show how our approach can provide better output than standard sampling techniques. We also show that the response validation step is a necessary complement to the response generation step.

replace-cross Reconciling Kaplan and Chinchilla Scaling Laws

Authors: Tim Pearce, Jinyeop Song

Abstract: Kaplan et al. [2020] (`Kaplan') and Hoffmann et al. [2022] (`Chinchilla') studied the scaling behavior of transformers trained on next-token language prediction. These studies produced different estimates for how the number of parameters ($N$) and training tokens ($D$) should be set to achieve the lowest possible loss for a given compute budget ($C$). Kaplan: $N_\text{optimal} \propto C^{0.73}$, Chinchilla: $N_\text{optimal} \propto C^{0.50}$. This paper finds that much of this discrepancy can be attributed to Kaplan counting non-embedding rather than total parameters, combined with their analysis being performed at small scale. Simulating the Chinchilla study under these conditions produces biased scaling coefficients close to Kaplan's. Hence, this paper reaffirms Chinchilla's scaling coefficients, by explaining the primary cause of Kaplan's original overestimation. As a second contribution, the paper explains differences in the reported relationships between loss and compute. These findings lead us to recommend that future scaling studies use total parameters and compute.

replace-cross A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Models

Authors: Dibaloke Chanda, Milan Aryal, Nasim Yahya Soltani, Masoud Ganji

Abstract: Recent advances in deep learning have completely transformed the domain of computational pathology (CPath). More specifically, it has altered the diagnostic workflow of pathologists by integrating foundation models (FMs) and vision-language models (VLMs) in their assessment and decision-making process. The limitations of existing deep learning approaches in CPath can be overcome by FMs through learning a representation space that can be adapted to a wide variety of downstream tasks without explicit supervision. Deploying VLMs allow pathology reports written in natural language be used as rich semantic information sources to improve existing models as well as generate predictions in natural language form. In this survey, a holistic and systematic overview of recent innovations in FMs and VLMs in CPath is presented. Furthermore, the tools, datasets and training schemes for these models are summarized in addition to categorizing them into distinct groups. This extensive survey highlights the current trends in CPath and its possible revolution through the use of FMs and VLMs in the future.

replace-cross ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework

Authors: Jiahao Yuan, Zixiang Di, Zhiqing Cui, Guisong Yang, Usman Naseem

Abstract: Empathetic response generation necessitates the integration of emotional and intentional dynamics to foster meaningful interactions. Existing research either neglects the intricate interplay between emotion and intent, leading to suboptimal controllability of empathy, or resorts to large language models (LLMs), which incur significant computational overhead. In this paper, we introduce ReflectDiffu, a lightweight and comprehensive framework for empathetic response generation. This framework incorporates emotion contagion to augment emotional expressiveness and employs an emotion-reasoning mask to pinpoint critical emotional elements. Additionally, it integrates intent mimicry within reinforcement learning for refinement during diffusion. By harnessing an intent twice reflect the mechanism of Exploring-Sampling-Correcting, ReflectDiffu adeptly translates emotional decision-making into precise intent actions, thereby addressing empathetic response misalignments stemming from emotional misrecognition. Through reflection, the framework maps emotional states to intents, markedly enhancing both response empathy and flexibility. Comprehensive experiments reveal that ReflectDiffu outperforms existing models regarding relevance, controllability, and informativeness, achieving state-of-the-art results in both automatic and human evaluations.

replace-cross RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Authors: Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu

Abstract: Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer contexts incurs extremely slow inference latency and high GPU memory consumption for caching key-value (KV) vectors. This paper proposes RetrievalAttention, a training-free approach to both accelerate attention computation and reduce GPU memory consumption. By leveraging the dynamic sparsity of attention mechanism, RetrievalAttention proposes to use approximate nearest neighbor search (ANNS) indexes for KV vectors in CPU memory and retrieves the most relevant ones with vector search during generation. Unfortunately, we observe that the off-the-shelf ANNS indexes are often ineffective for such retrieval tasks due to the out-of-distribution (OOD) between query vectors and key vectors in attention mechanism. RetrievalAttention addresses the OOD challenge by designing an attention-aware vector search algorithm that can adapt to the distribution of query vectors. Our evaluation shows that RetrievalAttention only needs to access 1--3% of data while maintaining high model accuracy. This leads to significant reduction in the inference cost of long-context LLMs with much lower GPU memory footprint. In particular, RetrievalAttention only needs a single NVIDIA RTX4090 (24GB) for serving 128K tokens in LLMs with 8B parameters, which is capable of generating one token in 0.188 seconds.