Authors: Daniele Grandi, Yash Patawari Jain, Allin Groom, Brandon Cramer, Christopher McComb
Abstract: Material selection is a crucial step in conceptual design due to its significant impact on the functionality, aesthetics, manufacturability, and sustainability impact of the final product. This study investigates the use of Large Language Models (LLMs) for material selection in the product design process and compares the performance of LLMs against expert choices for various design scenarios. By collecting a dataset of expert material preferences, the study provides a basis for evaluating how well LLMs can align with expert recommendations through prompt engineering and hyperparameter tuning. The divergence between LLM and expert recommendations is measured across different model configurations, prompt strategies, and temperature settings. This approach allows for a detailed analysis of factors influencing the LLMs' effectiveness in recommending materials. The results from this study highlight two failure modes, and identify parallel prompting as a useful prompt-engineering method when using LLMs for material selection. The findings further suggest that, while LLMs can provide valuable assistance, their recommendations often vary significantly from those of human experts. This discrepancy underscores the need for further research into how LLMs can be better tailored to replicate expert decision-making in material selection. This work contributes to the growing body of knowledge on how LLMs can be integrated into the design process, offering insights into their current limitations and potential for future improvements.
Authors: Wenjie Zhou, Zhenxin Ding, Xiaodong Zhang, Haibo Shi, Junfeng Wang, Dawei Yin
Abstract: Pre-trained language models have become an integral component of question-answering systems, achieving remarkable performance. For practical deployment, it is critical to carry out knowledge distillation to preserve high performance under computational constraints. In this paper, we address a key question: given the importance of unsupervised distillation for student performance, how does one effectively ensemble knowledge from multiple teachers at this stage without the guidance of ground-truth labels? We propose a novel algorithm, GOVERN, to tackle this issue. GOVERN has demonstrated significant improvements in both offline and online experiments. The proposed algorithm has been successfully deployed in a real-world commercial question-answering system.
Authors: Dengyi Liu, Minghao Wang, Andrew G. Catlin
Abstract: Academic researchers and social media entities grappling with the identification of hate speech face significant challenges, primarily due to the vast scale of data and the dynamic nature of hate speech. Given the ethical and practical limitations of large predictive models like ChatGPT in directly addressing such sensitive issues, our research has explored alternative advanced transformer-based and generative AI technologies since 2019. Specifically, we developed a new data labeling technique and established a proof of concept targeting anti-Semitic hate speech, utilizing a variety of transformer models such as BERT (arXiv:1810.04805), DistillBERT (arXiv:1910.01108), RoBERTa (arXiv:1907.11692), and LLaMA-2 (arXiv:2307.09288), complemented by the LoRA fine-tuning approach (arXiv:2106.09685). This paper delineates and evaluates the comparative efficacy of these cutting-edge methods in tackling the intricacies of hate speech detection, highlighting the need for responsible and carefully managed AI applications within sensitive contexts.
Authors: Christopher Clarke, Roland Daynauth, Charlene Wilkinson, Hubert Devonish, Jason Mars
Abstract: While major languages often enjoy substantial attention and resources, the linguistic diversity across the globe encompasses a multitude of smaller, indigenous, and regional languages that lack the same level of computational support. One such region is the Caribbean. While commonly labeled as "English speaking", the ex-British Caribbean region consists of a myriad of Creole languages thriving alongside English. In this paper, we present Guylingo: a comprehensive corpus designed for advancing NLP research in the domain of Creolese (Guyanese English-lexicon Creole), the most widely spoken language in the culturally rich nation of Guyana. We first outline our framework for gathering and digitizing this diverse corpus, inclusive of colloquial expressions, idioms, and regional variations in a low-resource language. We then demonstrate the challenges of training and evaluating NLP models for machine translation in Creole. Lastly, we discuss the unique opportunities presented by recent NLP advancements for accelerating the formal adoption of Creole languages as official languages in the Caribbean.
Authors: Guy Azov, Tatiana Pelc, Adi Fledel Alon, Gila Kamhi
Abstract: Previous studies have demonstrated that proactive interaction with user reviews has a positive impact on the perception of app users and encourages them to submit revised ratings. Nevertheless, developers encounter challenges in managing a high volume of reviews, particularly in the case of popular apps with a substantial influx of daily reviews. Consequently, there is a demand for automated solutions aimed at streamlining the process of responding to user reviews. To address this, we have developed a new system for generating automatic responses by leveraging user-contributed documents with the help of retrieval-augmented generation (RAG) and advanced Large Language Models (LLMs). Our solution, named SCRABLE, represents an adaptive customer review response automation that enhances itself with self-optimizing prompts and a judging mechanism based on LLMs. Additionally, we introduce an automatic scoring mechanism that mimics the role of a human evaluator to assess the quality of responses generated in customer review domains. Extensive experiments and analyses conducted on real-world datasets reveal that our method is effective in producing high-quality responses, yielding improvement of more than 8.5% compared to the baseline. Further validation through manual examination of the generated responses underscores the efficacy our proposed system.
Authors: Dainis Boumber, Rakesh M. Verma, Fatima Zahra Qachfar
Abstract: Deception, a prevalent aspect of human communication, has undergone a significant transformation in the digital age. With the globalization of online interactions, individuals are communicating in multiple languages and mixing languages on social media, with varied data becoming available in each language and dialect. At the same time, the techniques for detecting deception are similar across the board. Recent studies have shown the possibility of the existence of universal linguistic cues to deception across domains within the English language; however, the existence of such cues in other languages remains unknown. Furthermore, the practical task of deception detection in low-resource languages is not a well-studied problem due to the lack of labeled data. Another dimension of deception is multimodality. For example, a picture with an altered caption in fake news or disinformation may exist. This paper calls for a comprehensive investigation into the complexities of deceptive language across linguistic boundaries and modalities within the realm of computer security and natural language processing and the possibility of using multilingual transformer models and labeled data in various languages to universally address the task of deception detection.
Authors: Wenhao Wu, Yizhong Wang, Yao Fu, Xiang Yue, Dawei Zhu, Sujian Li
Abstract: Effectively handling instructions with extremely long context remains a challenge for Large Language Models (LLMs), typically necessitating high-quality long data and substantial computational resources. This paper introduces Step-Skipping Alignment (SkipAlign), a new technique designed to enhance the long-context capabilities of LLMs in the phase of alignment without the need for additional efforts beyond training with original data length. SkipAlign is developed on the premise that long-range dependencies are fundamental to enhancing an LLM's capacity of long context. Departing from merely expanding the length of input samples, SkipAlign synthesizes long-range dependencies from the aspect of positions indices. This is achieved by the strategic insertion of skipped positions within instruction-following samples, which utilizes the semantic structure of the data to effectively expand the context. Through extensive experiments on base models with a variety of context window sizes, SkipAlign demonstrates its effectiveness across a spectrum of long-context tasks. Particularly noteworthy is that with a careful selection of the base model and alignment datasets, SkipAlign with only 6B parameters achieves it's best performance and comparable with strong baselines like GPT-3.5-Turbo-16K on LongBench.
Authors: Xupeng Zha, Huan Zhao, Zixing Zhang
Abstract: Conversational Emotion Recognition (CER) aims to predict the emotion expressed by an utterance (referred to as an ``event'') during a conversation. Existing graph-based methods mainly focus on event interactions to comprehend the conversational context, while overlooking the direct influence of the speaker's emotional state on the events. In addition, real-time modeling of the conversation is crucial for real-world applications but is rarely considered. Toward this end, we propose a novel graph-based approach, namely Event-State Interactions infused Heterogeneous Graph Neural Network (ESIHGNN), which incorporates the speaker's emotional state and constructs a heterogeneous event-state interaction graph to model the conversation. Specifically, a heterogeneous directed acyclic graph neural network is employed to dynamically update and enhance the representations of events and emotional states at each turn, thereby improving conversational coherence and consistency. Furthermore, to further improve the performance of CER, we enrich the graph's edges with external knowledge. Experimental results on four publicly available CER datasets show the superiority of our approach and the effectiveness of the introduced heterogeneous event-state interaction graph.
Authors: Hassan Shakil, Zeydy Ortiz, Grant C. Forbes
Abstract: In this research, we uses the DistilBERT model to generate extractive summary and the T5 model to generate abstractive summaries. Also, we generate hybrid summaries by combining both DistilBERT and T5 models. Central to our research is the implementation of GPT-based refining process to minimize the common problem of hallucinations that happens in AI-generated summaries. We evaluate unrefined summaries and, after refining, we also assess refined summaries using a range of traditional and novel metrics, demonstrating marked improvements in the accuracy and reliability of the summaries. Results highlight significant improvements in reducing hallucinatory content, thereby increasing the factual integrity of the summaries.
Authors: Rapha\"el Milli\`ere
Abstract: Deep learning has enabled major advances across most areas of artificial intelligence research. This remarkable progress extends beyond mere engineering achievements and holds significant relevance for the philosophy of cognitive science. Deep neural networks have made significant strides in overcoming the limitations of older connectionist models that once occupied the centre stage of philosophical debates about cognition. This development is directly relevant to long-standing theoretical debates in the philosophy of cognitive science. Furthermore, ongoing methodological challenges related to the comparative evaluation of deep neural networks stand to benefit greatly from interdisciplinary collaboration with philosophy and cognitive science. The time is ripe for philosophers to explore foundational issues related to deep learning and cognition; this perspective paper surveys key areas where their contributions can be especially fruitful.
Authors: Hassan Shakil, Atqiya Munawara Mahi, Phuoc Nguyen, Zeydy Ortiz, Mamoun T. Mardini
Abstract: This research examines the effectiveness of OpenAI's GPT models as independent evaluators of text summaries generated by six transformer-based models from Hugging Face: DistilBART, BERT, ProphetNet, T5, BART, and PEGASUS. We evaluated these summaries based on essential properties of high-quality summary - conciseness, relevance, coherence, and readability - using traditional metrics such as ROUGE and Latent Semantic Analysis (LSA). Uniquely, we also employed GPT not as a summarizer but as an evaluator, allowing it to independently assess summary quality without predefined metrics. Our analysis revealed significant correlations between GPT evaluations and traditional metrics, particularly in assessing relevance and coherence. The results demonstrate GPT's potential as a robust tool for evaluating text summaries, offering insights that complement established metrics and providing a basis for comparative analysis of transformer-based models in natural language processing tasks.
Authors: Runheng Liu, Xingchen Xiao, Heyan Huang, Zewen Chi, Zhijing Wu
Abstract: Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training corpus. Previous work using utilizing retrieved content by simply prepending retrieved contents to the input poses a high runtime issue, which degrades the inference efficiency of the LLMs because they fail to use the Key-Value (KV) cache efficiently. In this paper, we propose \textsc{FlashBack}, a modular RALM designed to improve the inference efficiency of RALM with appending context pattern while maintaining decent performance after specific fine-tuning without heavily destruct the knowledge integrity of the LLM. \textsc{FlashBack} appends retrieved documents at the end of the context for efficiently utilizing the KV cache instead of prepending them. Our experiment shows that the inference speed of \textsc{FlashBack} is up to $4\times$ faster than the prepending method on a 7B LLM (Llama 2). Via bypassing unnecessary re-computation, it demonstrates an advancement by achieving significantly faster inference speed, and this heightened efficiency will substantially reduce inferential cost. Our code will be publicly available.
Authors: Yongqi Tong, Sizhe Wang, Dawei Li, Yifan Wang, Simeng Han, Zi Lin, Chengsong Huang, Jiaxin Huang, Jingbo Shang
Abstract: While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a small collection of annotated questions. Then it iteratively improves LLMs by learning from the differences in responses from the SFT and unfinetuned models on unlabeled questions. Our approach provides an efficient approach without relying heavily on extensive human-annotated explanations. However, current reasoning benchmarks typically only include golden-reference answers or rationales. Therefore, we present \textsc{PuzzleBen}, a weakly supervised benchmark that comprises 25,147 complex questions, answers, and human-generated rationales across various domains, such as brainteasers, puzzles, riddles, parajumbles, and critical reasoning tasks. A unique aspect of our dataset is the inclusion of 10,000 unannotated questions, enabling us to explore utilizing fewer supersized data to boost LLMs' inference capabilities. Our experiments underscore the significance of \textsc{PuzzleBen}, as well as the effectiveness of our methodology as a promising direction in future endeavors. Our dataset and code will be published soon on \texttt{Anonymity Link}.
Authors: Zhonglong Chen, Changwei Song, Yining Chen, Jianqiang Li, Guanghui Fu, Yongsheng Tong, Qing Zhao
Abstract: Suicide and suicidal behaviors remain significant challenges for public policy and healthcare. In response, psychological support hotlines have been established worldwide to provide immediate help to individuals in mental crises. The effectiveness of these hotlines largely depends on accurately identifying callers' emotional states, particularly underlying negative emotions indicative of increased suicide risk. However, the high demand for psychological interventions often results in a shortage of professional operators, highlighting the need for an effective speech emotion recognition model. This model would automatically detect and analyze callers' emotions, facilitating integration into hotline services. Additionally, it would enable large-scale data analysis of psychological support hotline interactions to explore psychological phenomena and behaviors across populations. Our study utilizes data from the Beijing psychological support hotline, the largest suicide hotline in China. We analyzed speech data from 105 callers containing 20,630 segments and categorized them into 11 types of negative emotions. We developed a negative emotion recognition model and a fine-grained multi-label classification model using a large-scale pre-trained model. Our experiments indicate that the negative emotion recognition model achieves a maximum F1-score of 76.96%. However, it shows limited efficacy in the fine-grained multi-label classification task, with the best model achieving only a 41.74% weighted F1-score. We conducted an error analysis for this task, discussed potential future improvements, and considered the clinical application possibilities of our study. All the codes are public available.
Authors: Zhixuan Chu, Yan Wang, Longfei Li, Zhibo Wang, Zhan Qin, Kui Ren
Abstract: Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs towards desired attributes often assume unbiased representations and rely solely on steering prompts. However, the representations learned from pre-training can introduce semantic biases that influence the steering process, leading to suboptimal results. We propose LLMGuardaril, a novel framework that incorporates causal analysis and adversarial learning to obtain unbiased steering representations in LLMs. LLMGuardaril systematically identifies and blocks the confounding effects of biases, enabling the extraction of unbiased steering representations. Additionally, it includes an explainable component that provides insights into the alignment between the generated output and the desired direction. Experiments demonstrate LLMGuardaril's effectiveness in steering LLMs towards desired attributes while mitigating biases. Our work contributes to the development of safe and reliable LLMs that align with desired attributes. We discuss the limitations and future research directions, highlighting the need for ongoing research to address the ethical implications of large language models.
Authors: Gunjan Balde, Soumyadeep Roy, Mainack Mondal, Niloy Ganguly
Abstract: This work presents a dynamic vocabulary adaptation strategy, MEDVOC, for fine-tuning pre-trained language models (PLMs) like BertSumAbs, BART, and PEGASUS for improved medical text summarization. In contrast to existing domain adaptation approaches in summarization, MEDVOC treats vocabulary as an optimizable parameter and optimizes the PLM vocabulary based on fragment score conditioned only on the downstream task's reference summaries. Unlike previous works on vocabulary adaptation (limited only to classification tasks), optimizing vocabulary based on summarization tasks requires an extremely costly intermediate fine-tuning step on large summarization datasets. To that end, our novel fragment score-based hyperparameter search very significantly reduces this fine-tuning time -- from 450 days to less than 2 days on average. Furthermore, while previous works on vocabulary adaptation are often primarily tied to single PLMs, MEDVOC is designed to be deployable across multiple PLMs (with varying model vocabulary sizes, pre-training objectives, and model sizes) -- bridging the limited vocabulary overlap between the biomedical literature domain and PLMs. MEDVOC outperforms baselines by 15.74% in terms of Rouge-L in zero-shot setting and shows gains of 17.29% in high Out-Of-Vocabulary (OOV) concentrations. Our human evaluation shows MEDVOC generates more faithful medical summaries (88% compared to 59% in baselines). We make the codebase publicly available at https://github.com/gb-kgp/MEDVOC.
Authors: Jasraj Singh, Fang Liu, Hong Xu, Bee Chin Ng, Wei Zhang
Abstract: Nowadays, Information spreads at an unprecedented pace in social media and discerning truth from misinformation and fake news has become an acute societal challenge. Machine learning (ML) models have been employed to identify fake news but are far from perfect with challenging problems like limited accuracy, interpretability, and generalizability. In this paper, we enhance ML-based solutions with linguistics input and we propose LingML, linguistic-informed ML, for fake news detection. We conducted an experimental study with a popular dataset on fake news during the pandemic. The experiment results show that our proposed solution is highly effective. There are fewer than two errors out of every ten attempts with only linguistic input used in ML and the knowledge is highly explainable. When linguistics input is integrated with advanced large-scale ML models for natural language processing, our solution outperforms existing ones with 1.8% average error rate. LingML creates a new path with linguistics to push the frontier of effective and efficient fake news detection. It also sheds light on real-world multi-disciplinary applications requiring both ML and domain expertise to achieve optimal performance.
Authors: Duygu Altinok
Abstract: Large language models (LLMs) have garnered significant attention and widespread usage due to their impressive performance in various tasks. However, they are not without their own set of challenges, including issues such as hallucinations, factual inconsistencies, and limitations in numerical-quantitative reasoning. Evaluating LLMs in miscellaneous reasoning tasks remains an active area of research. Prior to the breakthrough of LLMs, Transformers had already proven successful in the medical domain, effectively employed for various natural language understanding (NLU) tasks. Following this trend, LLMs have also been trained and utilized in the medical domain, raising concerns regarding factual accuracy, adherence to safety protocols, and inherent limitations. In this paper, we focus on evaluating the natural language inference capabilities of popular open-source and closed-source LLMs using clinical trial reports as the dataset. We present the performance results of each LLM and further analyze their performance on a development set, particularly focusing on challenging instances that involve medical abbreviations and require numerical-quantitative reasoning. Gemini, our leading LLM, achieved a test set F1-score of 0.748, securing the ninth position on the task scoreboard. Our work is the first of its kind, offering a thorough examination of the inference capabilities of LLMs within the medical domain.
Authors: Chen Qian, Jiahao Li, Yufan Dang, Wei Liu, YiFei Wang, Zihao Xie, Weize Chen, Cheng Yang, Yingli Zhang, Zhiyuan Liu, Maosong Sun
Abstract: Autonomous agents powered by large language models (LLMs) show significant potential for achieving high autonomy in various scenarios such as software development. Recent research has shown that LLM agents can leverage past experiences to reduce errors and enhance efficiency. However, the static experience paradigm, reliant on a fixed collection of past experiences acquired heuristically, lacks iterative refinement and thus hampers agents' adaptability. In this paper, we introduce the Iterative Experience Refinement framework, enabling LLM agents to refine experiences iteratively during task execution. We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquiring experiences across all previous task batches. Augmented with our heuristic experience elimination, the method prioritizes high-quality and frequently-used experiences, effectively managing the experience space and enhancing efficiency. Extensive experiments show that while the successive pattern may yield superior results, the cumulative pattern provides more stable performance. Moreover, experience elimination facilitates achieving better performance using just 11.54% of a high-quality subset.
Authors: Arne Rubehn, Jessica Nieder, Robert Forkel, Johann-Mattis List
Abstract: When comparing speech sounds across languages, scholars often make use of feature representations of individual sounds in order to determine fine-grained sound similarities. Although binary feature systems for large numbers of speech sounds have been proposed, large-scale computational applications often face the challenges that the proposed feature systems -- even if they list features for several thousand sounds -- only cover a smaller part of the numerous speech sounds reflected in actual cross-linguistic data. In order to address the problem of missing data for attested speech sounds, we propose a new approach that can create binary feature vectors dynamically for all sounds that can be represented in the the standardized version of the International Phonetic Alphabet proposed by the Cross-Linguistic Transcription Systems (CLTS) reference catalog. Since CLTS is actively used in large data collections, covering more than 2,000 distinct language varieties, our procedure for the generation of binary feature vectors provides immediate access to a very large collection of multilingual wordlists. Testing our feature system in different ways on different datasets proves that the system is not only useful to provide a straightforward means to compare the similarity of speech sounds, but also illustrates its potential to be used in future cross-linguistic machine learning applications.
Authors: Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xuebo Liu, Lidia S. Chao, Min Zhang
Abstract: The efficacy of an large language model (LLM) generated text detector depends substantially on the availability of sizable training data. White-box zero-shot detectors, which require no such data, are nonetheless limited by the accessibility of the source model of the LLM-generated text. In this paper, we propose an simple but effective black-box zero-shot detection approach, predicated on the observation that human-written texts typically contain more grammatical errors than LLM-generated texts. This approach entails computing the Grammar Error Correction Score (GECScore) for the given text to distinguish between human-written and LLM-generated text. Extensive experimental results show that our method outperforms current state-of-the-art (SOTA) zero-shot and supervised methods, achieving an average AUROC of 98.7% and showing strong robustness against paraphrase and adversarial perturbation attacks.
Authors: Sayantan Pal, Souvik Das, Rohini K. Srihari
Abstract: This study introduces 'clickbait spoiling', a novel technique designed to detect, categorize, and generate spoilers as succinct text responses, countering the curiosity induced by clickbait content. By leveraging a multi-task learning framework, our model's generalization capabilities are significantly enhanced, effectively addressing the pervasive issue of clickbait. The crux of our research lies in generating appropriate spoilers, be it a phrase, an extended passage, or multiple, depending on the spoiler type required. Our methodology integrates two crucial techniques: a refined spoiler categorization method and a modified version of the Question Answering (QA) mechanism, incorporated within a multi-task learning paradigm for optimized spoiler extraction from context. Notably, we have included fine-tuning methods for models capable of handling longer sequences to accommodate the generation of extended spoilers. This research highlights the potential of sophisticated text processing techniques in tackling the omnipresent issue of clickbait, promising an enhanced user experience in the digital realm.
Authors: Ryan Whetten, Titouan Parcollet, Marco Dinarelli, Yannick Est\`eve
Abstract: Self-Supervised Learning (SSL) has proven to be useful in various speech tasks. However, these methods are generally very demanding in terms of data, memory, and computational resources. BERT-based Speech pre-Training with Random-projection Quantizer (BEST-RQ), is an SSL method that has shown great performance on Automatic Speech Recognition (ASR) while being simpler than other SSL methods, such as wav2vec 2.0. Despite BEST-RQ's great performance, details are lacking in the original paper, such as the amount of GPU/TPU hours used in pre-training, and there is no official easy-to-use open-source implementation. Furthermore, BEST-RQ has not been evaluated on other downstream tasks aside from ASR and speech translation. In this work, we describe a re-implementation of a Random-projection quantizer and perform a preliminary study with a comparison to wav2vec 2.0 on four downstream tasks. We discuss the details and differences of our implementation. We show that a random projection quantizer can achieve similar downstream performance as wav2vec 2.0 while decreasing training time by over a factor of two.
Authors: Jonathan Mamou, Oren Pereg, Daniel Korat, Moshe Berchansky, Nadav Timor, Moshe Wasserblat, Roy Schwartz
Abstract: Speculative decoding is a promising method for reducing the inference latency of large language models. The effectiveness of the method depends on the speculation length (SL) - the number of tokens generated by the draft model at each iteration. The vast majority of speculative decoding approaches use the same SL for all iterations. In this work, we show that this practice is suboptimal. We introduce DISCO, a DynamIc SpeCulation length Optimization method that uses a classifier to dynamically adjust the SL at each iteration, while provably preserving the decoding quality. Experiments with four benchmarks demonstrate average speedup gains of 10.3% relative to our best baselines.
Authors: Atharvan Dogra, Ameet Deshpande, John Nay, Tanmay Rajpurohit, Ashwin Kalyan, Balaraman Ravindran
Abstract: Recent developments in large language models (LLMs), while offering a powerful foundation for developing natural language agents, raise safety concerns about them and the autonomous agents built upon them. Deception is one potential capability of AI agents of particular concern, which we refer to as an act or statement that misleads, hides the truth, or promotes a belief that is not true in its entirety or in part. We move away from the conventional understanding of deception through straight-out lying, making objective selfish decisions, or giving false information, as seen in previous AI safety research. We target a specific category of deception achieved through obfuscation and equivocation. We broadly explain the two types of deception by analogizing them with the rabbit-out-of-hat magic trick, where (i) the rabbit either comes out of a hidden trap door or (ii) (our focus) the audience is completely distracted to see the magician bring out the rabbit right in front of them using sleight of hand or misdirection. Our novel testbed framework displays intrinsic deception capabilities of LLM agents in a goal-driven environment when directed to be deceptive in their natural language generations in a two-agent adversarial dialogue system built upon the legislative task of "lobbying" for a bill. Along the lines of a goal-driven environment, we show developing deceptive capacity through a reinforcement learning setup, building it around the theories of language philosophy and cognitive psychology. We find that the lobbyist agent increases its deceptive capabilities by ~ 40% (relative) through subsequent reinforcement trials of adversarial interactions, and our deception detection mechanism shows a detection capability of up to 92%. Our results highlight potential issues in agent-human interaction, with agents potentially manipulating humans towards its programmed end-goal.
Authors: DeepSeek-AI
Abstract: We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models. The model checkpoints are available at "https://github.com/deepseek-ai/DeepSeek-V2".
Authors: Richard Zhu
Abstract: Exact nearest neighbor search is a computationally intensive process, and even its simpler sibling -- vector retrieval -- can be computationally complex. This is exacerbated when retrieving vectors which have high-dimension $d$ relative to the number of vectors, $N$, in the database. Exact nearest neighbor retrieval has been generally acknowledged to be a $O(Nd)$ problem with no sub-linear solutions. Attention has instead shifted towards Approximate Nearest-Neighbor (ANN) retrieval techniques, many of which have sub-linear or even logarithmic time complexities. However, if our intuition from binary search problems (e.g. $d=1$ vector retrieval) carries, there ought to be a way to retrieve an organized representation of vectors without brute-forcing our way to a solution. For low dimension (e.g. $d=2$ or $d=3$ cases), \texttt{kd-trees} provide a $O(d\log N)$ algorithm for retrieval. Unfortunately the algorithm deteriorates rapidly to a $O(dN)$ solution at high dimensions (e.g. $k=128$), in practice. We propose a novel algorithm for logarithmic Fast Exact Retrieval for Nearest-neighbor lookup (FERN), inspired by \texttt{kd-trees}. The algorithm achieves $O(d\log N)$ look-up with 100\% recall on 10 million $d=128$ uniformly randomly generated vectors.\footnote{Code available at https://github.com/RichardZhu123/ferns}
Authors: Alexis Ross, Jacob Andreas
Abstract: When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what students already know and adapt their teaching to students' changing state of knowledge. There is increasing interest in using computational models, particularly large language models, as pedagogical tools. As students, language models in particular have shown a remarkable ability to adapt to new tasks given small numbers of examples. But how effectively can these models adapt as teachers to students of different types? To study this question, we introduce a suite of models and evaluation methods we call AdapT. AdapT has two components: (1) a collection of simulated Bayesian student models that can be used for evaluation of automated teaching methods; (2) a platform for evaluation with human students, to characterize the real-world effectiveness of these methods. We additionally introduce (3) AToM, a new probabilistic model for adaptive teaching that jointly infers students' past beliefs and optimizes for the correctness of future beliefs. In evaluations of simulated students across three learning domains (fraction arithmetic, English morphology, function learning), AToM systematically outperforms LLM-based and standard Bayesian teaching models. In human experiments, both AToM and LLMs outperform non-adaptive random example selection. Our results highlight both the difficulty of the adaptive teaching task and the potential of learned adaptive models for solving it.
Authors: Shujian Zhang, Korawat Tanwisuth, Chengyue Gong, Pengcheng He, Mingyuan Zhou
Abstract: Auto-regressive generation models achieve competitive performance across many different NLP tasks such as summarization, question answering, and classifications. However, they are also known for being slow in inference, which makes them challenging to deploy in real-time applications. We propose a switchable decision to accelerate inference by dynamically assigning computation resources for each data instance. Automatically making decisions on where to skip and how to balance quality and computation cost with constrained optimization, our dynamic neural generation networks enforce the efficient inference path and determine the optimized trade-off. Experiments across question answering, summarization, and classification benchmarks show that our method benefits from less computation cost during inference while keeping the same accuracy. Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
Authors: Jiaoda Li, Jennifer C. White, Mrinmaya Sachan, Ryan Cotterell
Abstract: Natural languages are believed to be (mildly) context-sensitive. Despite underpinning remarkably capable large language models, transformers are unable to model many context-free language tasks. In an attempt to address this limitation in the modeling power of transformer-based language models, we propose augmenting them with a differentiable, stack-based attention mechanism. Our stack-based attention mechanism can be incorporated into any transformer-based language model and adds a level of interpretability to the model. We show that the addition of our stack-based attention mechanism enables the transformer to model some, but not all, deterministic context-free languages.
Authors: Shudan Zhang, Hanlin Zhao, Xiao Liu, Qinkai Zheng, Zehan Qi, Xiaotao Gu, Xiaohan Zhang, Yuxiao Dong, Jie Tang
Abstract: Large language models (LLMs) have manifested strong ability to generate codes for productive activities. However, current benchmarks for code synthesis, such as HumanEval, MBPP, and DS-1000, are predominantly oriented towards introductory tasks on algorithm and data science, insufficiently satisfying challenging requirements prevalent in real-world coding. To fill this gap, we propose NaturalCodeBench (NCB), a challenging code benchmark designed to mirror the complexity and variety of scenarios in real coding tasks. NCB comprises 402 high-quality problems in Python and Java, meticulously selected from natural user queries from online coding services, covering 6 different domains. Noting the extraordinary difficulty in creating testing cases for real-world queries, we also introduce a semi-automated pipeline to enhance the efficiency of test case construction. Comparing with manual solutions, it achieves an efficiency increase of more than 4 times. Our systematic experiments on 39 LLMs find that performance gaps on NCB between models with close HumanEval scores could still be significant, indicating a lack of focus on practical code synthesis scenarios or over-specified optimization on HumanEval. On the other hand, even the best-performing GPT-4 is still far from satisfying on NCB. The evaluation toolkit and development set are available at https://github.com/THUDM/NaturalCodeBench.
Authors: Yujun Lin, Haotian Tang, Shang Yang, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han
Abstract: Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. Nonetheless, state-of-the-art INT4 quantization techniques only accelerate low-batch, edge LLM inference, failing to deliver performance gains in large-batch, cloud-based LLM serving. We uncover a critical issue: existing INT4 quantization methods suffer from significant runtime overhead (20-90%) when dequantizing either weights or partial sums on GPUs. To address this challenge, we introduce QoQ, a W4A8KV4 quantization algorithm with 4-bit weight, 8-bit activation, and 4-bit KV cache. QoQ stands for quattuor-octo-quattuor, which represents 4-8-4 in Latin. QoQ is implemented by the QServe inference library that achieves measured speedup. The key insight driving QServe is that the efficiency of LLM serving on GPUs is critically influenced by operations on low-throughput CUDA cores. Building upon this insight, in QoQ algorithm, we introduce progressive quantization that can allow low dequantization overhead in W4A8 GEMM. Additionally, we develop SmoothAttention to effectively mitigate the accuracy degradation incurred by 4-bit KV quantization. In the QServe system, we perform compute-aware weight reordering and take advantage of register-level parallelism to reduce dequantization latency. We also make fused attention memory-bound, harnessing the performance gain brought by KV4 quantization. As a result, QServe improves the maximum achievable serving throughput of Llama-3-8B by 1.2x on A100, 1.4x on L40S; and Qwen1.5-72B by 2.4x on A100, 3.5x on L40S, compared to TensorRT-LLM. Remarkably, QServe on L40S GPU can achieve even higher throughput than TensorRT-LLM on A100. Thus, QServe effectively reduces the dollar cost of LLM serving by 3x. Code is available at https://github.com/mit-han-lab/qserve.
Authors: Razan Baltaji, Babak Hemmatian, Lav R. Varshney
Abstract: This study explores the sources of instability in maintaining cultural personas and opinions within multi-agent LLM systems. Drawing on simulations of inter-cultural collaboration and debate, we analyze agents' pre- and post-discussion private responses alongside chat transcripts to assess the stability of cultural personas and the impact of opinion diversity on group outcomes. Our findings suggest that multi-agent discussions can encourage collective decisions that reflect diverse perspectives, yet this benefit is tempered by the agents' susceptibility to conformity due to perceived peer pressure and challenges in maintaining consistent personas and opinions. Counterintuitively, instructions that encourage debate in support of one's opinions increase the rate of inconstancy. Without addressing the factors we identify, the full potential of multi-agent frameworks for producing more culturally diverse AI outputs will remain untapped.
Authors: Tyler Bikaun, Michael Stewart, Wei Liu
Abstract: This paper presents CleanGraph, an interactive web-based tool designed to facilitate the refinement and completion of knowledge graphs. Maintaining the reliability of knowledge graphs, which are grounded in high-quality and error-free facts, is crucial for real-world applications such as question-answering and information retrieval systems. These graphs are often automatically assembled from textual sources by extracting semantic triples via information extraction. However, assuring the quality of these extracted triples, especially when dealing with large or low-quality datasets, can pose a significant challenge and adversely affect the performance of downstream applications. CleanGraph allows users to perform Create, Read, Update, and Delete (CRUD) operations on their graphs, as well as apply models in the form of plugins for graph refinement and completion tasks. These functionalities enable users to enhance the integrity and reliability of their graph data. A demonstration of CleanGraph and its source code can be accessed at https://github.com/nlp-tlp/CleanGraph under the MIT License.
Authors: Zhongren Dong, Zixing Zhang, Weixiang Xu, Jing Han, Jianjun Ou, Bj\"orn W. Schuller
Abstract: Automatically detecting Alzheimer's Disease (AD) from spontaneous speech plays an important role in its early diagnosis. Recent approaches highly rely on the Transformer architectures due to its efficiency in modelling long-range context dependencies. However, the quadratic increase in computational complexity associated with self-attention and the length of audio poses a challenge when deploying such models on edge devices. In this context, we construct a novel framework, namely Hierarchical Attention-Free Transformer (HAFFormer), to better deal with long speech for AD detection. Specifically, we employ an attention-free module of Multi-Scale Depthwise Convolution to replace the self-attention and thus avoid the expensive computation, and a GELU-based Gated Linear Unit to replace the feedforward layer, aiming to automatically filter out the redundant information. Moreover, we design a hierarchical structure to force it to learn a variety of information grains, from the frame level to the dialogue level. By conducting extensive experiments on the ADReSS-M dataset, the introduced HAFFormer can achieve competitive results (82.6% accuracy) with other recent work, but with significant computational complexity and model size reduction compared to the standard Transformer. This shows the efficiency of HAFFormer in dealing with long audio for AD detection.
Authors: Chen Zhu-Tian, Zeyu Xiong, Xiaoshuo Yao, Elena Glassman
Abstract: Crafting effective prompts for code generation or editing with Large Language Models (LLMs) is not an easy task. Particularly, the absence of immediate, stable feedback during prompt crafting hinders effective interaction, as users are left to mentally imagine possible outcomes until the code is generated. In response, we introduce Language-Oriented Code Sketching, an interactive approach that provides instant, incremental feedback in the form of code sketches (i.e., incomplete code outlines) during prompt crafting. This approach converts a prompt into a code sketch by leveraging the inherent linguistic structures within the prompt and applying classic natural language processing techniques. The sketch then serves as an intermediate placeholder that not only previews the intended code structure but also guides the LLM towards the desired code, thereby enhancing human-LLM interaction. We conclude by discussing the approach's applicability and future plans.
Authors: Megha Srivastava, Cedric Colas, Dorsa Sadigh, Jacob Andreas
Abstract: Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like features such as generalization, interpretability and human inter-operability. Inspired by the rich interactions between language and decision-making in humans, we introduce Policy Learning with a Language Bottleneck (PLLB), a framework enabling AI agents to generate linguistic rules that capture the strategies underlying their most rewarding behaviors. PLLB alternates between a rule generation step guided by language models, and an update step where agents learn new policies guided by rules. In a two-player communication game, a maze solving task, and two image reconstruction tasks, we show that PLLB agents are not only able to learn more interpretable and generalizable behaviors, but can also share the learned rules with human users, enabling more effective human-AI coordination.
Authors: Benjamin Wolff, Eva Seidlmayer, Konrad U. F\"orstner
Abstract: With the rapid expansion of academic literature and the proliferation of preprints, researchers face growing challenges in manually organizing and labeling large volumes of articles. The NSLP 2024 FoRC Shared Task I addresses this challenge organized as a competition. The goal is to develop a classifier capable of predicting one of 123 predefined classes from the Open Research Knowledge Graph (ORKG) taxonomy of research fields for a given article.This paper presents our results. Initially, we enrich the dataset (containing English scholarly articles sourced from ORKG and arXiv), then leverage different pre-trained language Models (PLMs), specifically BERT, and explore their efficacy in transfer learning for this downstream task. Our experiments encompass feature-based and fine-tuned transfer learning approaches using diverse PLMs, optimized for scientific tasks, including SciBERT, SciNCL, and SPECTER2. We conduct hyperparameter tuning and investigate the impact of data augmentation from bibliographic databases such as OpenAlex, Semantic Scholar, and Crossref. Our results demonstrate that fine-tuning pre-trained models substantially enhances classification performance, with SPECTER2 emerging as the most accurate model. Moreover, enriching the dataset with additional metadata improves classification outcomes significantly, especially when integrating information from S2AG, OpenAlex and Crossref. Our best-performing approach achieves a weighted F1-score of 0.7415. Overall, our study contributes to the advancement of reliable automated systems for scholarly publication categorization, offering a potential solution to the laborious manual curation process, thereby facilitating researchers in efficiently locating relevant resources.
Authors: Mayank Mishra, Matt Stallone, Gaoyuan Zhang, Yikang Shen, Aditya Prasad, Adriana Meza Soria, Michele Merler, Parameswaran Selvam, Saptha Surendran, Shivdeep Singh, Manish Sethi, Xuan-Hong Dang, Pengyuan Li, Kun-Lung Wu, Syed Zawad, Andrew Coleman, Matthew White, Mark Lewis, Raju Pavuluri, Yan Koyfman, Boris Lublinsky, Maximilien de Bayser, Ibrahim Abdelaziz, Kinjal Basu, Mayank Agarwal, Yi Zhou, Chris Johnson, Aanchal Goyal, Hima Patel, Yousaf Shah, Petros Zerfos, Heiko Ludwig, Asim Munawar, Maxwell Crouse, Pavan Kapanipathi, Shweta Salaria, Bob Calio, Sophia Wen, Seetharami Seelam, Brian Belgodere, Carlos Fonseca, Amith Singhee, Nirmit Desai, David D. Cox, Ruchir Puri, Rameswar Panda
Abstract: Large Language Models (LLMs) trained on code are revolutionizing the software development process. Increasingly, code LLMs are being integrated into software development environments to improve the productivity of human programmers, and LLM-based agents are beginning to show promise for handling complex tasks autonomously. Realizing the full potential of code LLMs requires a wide range of capabilities, including code generation, fixing bugs, explaining and documenting code, maintaining repositories, and more. In this work, we introduce the Granite series of decoder-only code models for code generative tasks, trained with code written in 116 programming languages. The Granite Code models family consists of models ranging in size from 3 to 34 billion parameters, suitable for applications ranging from complex application modernization tasks to on-device memory-constrained use cases. Evaluation on a comprehensive set of tasks demonstrates that Granite Code models consistently reaches state-of-the-art performance among available open-source code LLMs. The Granite Code model family was optimized for enterprise software development workflows and performs well across a range of coding tasks (e.g. code generation, fixing and explanation), making it a versatile all around code model. We release all our Granite Code models under an Apache 2.0 license for both research and commercial use.
Authors: Elias Abad Rocamora, Yongtao Wu, Fanghui Liu, Grigorios G. Chrysos, Volkan Cevher
Abstract: Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adversarial examples. While character-level attacks easily maintain semantics, they have received less attention as they cannot easily adopt popular gradient-based methods, and are thought to be easy to defend. Challenging these beliefs, we introduce Charmer, an efficient query-based adversarial attack capable of achieving high attack success rate (ASR) while generating highly similar adversarial examples. Our method successfully targets both small (BERT) and large (Llama 2) models. Specifically, on BERT with SST-2, Charmer improves the ASR in 4.84% points and the USE similarity in 8% points with respect to the previous art. Our implementation is available in https://github.com/LIONS-EPFL/Charmer.
Authors: Xiao Liu, Chenxu Zhang, Lei Zhang
Abstract: State Space Model (SSM) is a mathematical model used to describe and analyze the behavior of dynamic systems. This model has witnessed numerous applications in several fields, including control theory, signal processing, economics and machine learning. In the field of deep learning, state space models are used to process sequence data, such as time series analysis, natural language processing (NLP) and video understanding. By mapping sequence data to state space, long-term dependencies in the data can be better captured. In particular, modern SSMs have shown strong representational capabilities in NLP, especially in long sequence modeling, while maintaining linear time complexity. Notably, based on the latest state-space models, Mamba merges time-varying parameters into SSMs and formulates a hardware-aware algorithm for efficient training and inference. Given its impressive efficiency and strong long-range dependency modeling capability, Mamba is expected to become a new AI architecture that may outperform Transformer. Recently, a number of works have attempted to study the potential of Mamba in various fields, such as general vision, multi-modal, medical image analysis and remote sensing image analysis, by extending Mamba from natural language domain to visual domain. To fully understand Mamba in the visual domain, we conduct a comprehensive survey and present a taxonomy study. This survey focuses on Mamba's application to a variety of visual tasks and data types, and discusses its predecessors, recent advances and far-reaching impact on a wide range of domains. Since Mamba is now on an upward trend, please actively notice us if you have new findings, and new progress on Mamba will be included in this survey in a timely manner and updated on the Mamba project at https://github.com/lx6c78/Vision-Mamba-A-Comprehensive-Survey-and-Taxonomy.
URLs: https://github.com/lx6c78/Vision-Mamba-A-Comprehensive-Survey-and-Taxonomy.
Authors: Muhammad ElNokrashy, Badr AlKhamissi, Mona Diab
Abstract: Language Models pretrained on large textual data have been shown to encode different types of knowledge simultaneously. Traditionally, only the features from the last layer are used when adapting to new tasks or data. We put forward that, when using or finetuning deep pretrained models, intermediate layer features that may be relevant to the downstream task are buried too deep to be used efficiently in terms of needed samples or steps. To test this, we propose a new layer fusion method: Depth-Wise Attention (DWAtt), to help re-surface signals from non-final layers. We compare DWAtt to a basic concatenation-based layer fusion method (Concat), and compare both to a deeper model baseline -- all kept within a similar parameter budget. Our findings show that DWAtt and Concat are more step- and sample-efficient than the baseline, especially in the few-shot setting. DWAtt outperforms Concat on larger data sizes. On CoNLL-03 NER, layer fusion shows 3.68--9.73% F1 gain at different few-shot sizes. The layer fusion models presented significantly outperform the baseline in various training scenarios with different data sizes, architectures, and training constraints.
Authors: Yiwei Wang, Bryan Hooi, Fei Wang, Yujun Cai, Yuxuan Liang, Wenxuan Zhou, Jing Tang, Manjuan Duan, Muhao Chen
Abstract: Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context. However, existing work has found that the RE models memorize the entity name patterns to make RE predictions while ignoring the textual context. This motivates us to raise the question: ``are RE models robust to the entity replacements?'' In this work, we operate the random and type-constrained entity replacements over the RE instances in TACRED and evaluate the state-of-the-art RE models under the entity replacements. We observe the 30\% - 50\% F1 score drops on the state-of-the-art RE models under entity replacements. These results suggest that we need more efforts to develop effective RE models robust to entity replacements. We release the source code at https://github.com/wangywUST/RobustRE.
Authors: Dana Arad, Hadas Orgad, Yonatan Belinkov
Abstract: Our world is marked by unprecedented technological, global, and socio-political transformations, posing a significant challenge to text-to-image generative models. These models encode factual associations within their parameters that can quickly become outdated, diminishing their utility for end-users. To that end, we introduce ReFACT, a novel approach for editing factual associations in text-to-image models without relaying on explicit input from end-users or costly re-training. ReFACT updates the weights of a specific layer in the text encoder, modifying only a tiny portion of the model's parameters and leaving the rest of the model unaffected. We empirically evaluate ReFACT on an existing benchmark, alongside a newly curated dataset. Compared to other methods, ReFACT achieves superior performance in both generalization to related concepts and preservation of unrelated concepts. Furthermore, ReFACT maintains image generation quality, making it a practical tool for updating and correcting factual information in text-to-image models.
Authors: Wenqi Zhang, Yongliang Shen, Weiming Lu, Yueting Zhuang
Abstract: Various industries such as finance, meteorology, and energy produce vast amounts of heterogeneous data every day. There is a natural demand for humans to manage, process, and display data efficiently. However, it necessitates labor-intensive efforts and a high level of expertise for these data-related tasks. Considering large language models (LLMs) showcase promising capabilities in semantic understanding and reasoning, we advocate that the deployment of LLMs could autonomously manage and process massive amounts of data while interacting and displaying in a human-friendly manner. Based on this, we propose Data-Copilot, an LLM-based system that connects numerous data sources on one end and caters to diverse human demands on the other end. Acting as an experienced expert, Data-Copilot autonomously transforms raw data into multi-form output that best matches the user's intent. Specifically, it first designs multiple universal interfaces to satisfy diverse data-related requests, like querying, analysis, prediction, and visualization. In real-time response, it automatically deploys a concise workflow by invoking corresponding interfaces. The whole process is fully controlled by Data-Copilot, without human assistance. We release Data-Copilot-1.0 using massive Chinese financial data, e.g., stocks, funds, and news. Experiments indicate it achieves reliable performance with lower token consumption, showing promising application prospects.
Authors: Shihong Liu, Zhiqiu Lin, Samuel Yu, Ryan Lee, Tiffany Ling, Deepak Pathak, Deva Ramanan
Abstract: Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities on downstream tasks when fine-tuned with minimal data. However, many VLMs rely on proprietary data and are not open-source, which restricts the use of white-box approaches for fine-tuning. As such, we aim to develop a black-box approach to optimize VLMs through natural language prompts, thereby avoiding the need to access model parameters, feature embeddings, or even output logits. We propose employing chat-based LLMs to search for the best text prompt for VLMs. Specifically, we adopt an automatic hill-climbing procedure that converges to an effective prompt by evaluating the performance of current prompts and asking LLMs to refine them based on textual feedback, all within a conversational process without human-in-the-loop. In a challenging 1-shot image classification setup, our simple approach surpasses the white-box continuous prompting method (CoOp) by an average of 1.5% across 11 datasets including ImageNet. Our approach also outperforms both human-engineered and LLM-generated prompts. We highlight the advantage of conversational feedback that incorporates both positive and negative prompts, suggesting that LLMs can utilize the implicit gradient direction in textual feedback for a more efficient search. In addition, we find that the text prompts generated through our strategy are not only more interpretable but also transfer well across different VLM architectures in a black-box manner. Lastly, we apply our framework to optimize the state-of-the-art black-box VLM (DALL-E 3) for text-to-image generation, prompt inversion, and personalization.
Authors: Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, Chao Huang
Abstract: Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a graph-oriented LLM capable of exceptional generalization across various datasets and tasks without relying on downstream graph data. We introduce the GraphGPT framework, which integrates LLMs with graph structural knowledge through graph instruction tuning. This framework includes a text-graph grounding component to link textual and graph structures and a dual-stage instruction tuning approach with a lightweight graph-text alignment projector. These innovations allow LLMs to comprehend complex graph structures and enhance adaptability across diverse datasets and tasks. Our framework demonstrates superior generalization in both supervised and zero-shot graph learning tasks, surpassing existing benchmarks. The open-sourced model implementation of our GraphGPT is available at https://github.com/HKUDS/GraphGPT.
Authors: Gantavya Bhatt, Yifang Chen, Arnav M. Das, Jifan Zhang, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak
Abstract: Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability in the context of LLMs. To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design. Experimental design techniques select the most informative samples to label, and typically maximize some notion of uncertainty and/or diversity. In our work, we implement a framework that evaluates several existing and novel experimental design techniques and find that these methods consistently yield significant gains in label efficiency with little computational overhead. On generative tasks, our methods achieve the same generalization performance with only $50\%$ of annotation cost required by random sampling.
Authors: Matan Avitan, Ryan Cotterell, Yoav Goldberg, Shauli Ravfogel
Abstract: Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. Such methods are employed, for example, to eliminate or alter the encoding of demographic information such as gender within the model's representations and, in so doing, create a counterfactual representation. However, because the intervention operates within the representation space, understanding precisely what aspects of the text it modifies poses a challenge. In this paper, we give a method to convert representation counterfactuals into string counterfactuals. We demonstrate that this approach enables us to analyze the linguistic alterations corresponding to a given representation space intervention and to interpret the features utilized to encode a specific concept. Moreover, the resulting counterfactuals can be used to mitigate bias in classification through data augmentation.
Authors: Danna Zheng, Danyang Liu, Mirella Lapata, Jeff Z. Pan
Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. However, concerns have arisen regarding the trustworthiness of LLMs outputs, particularly in closed-book question-answering tasks, where non-experts may struggle to identify inaccuracies due to the absence of contextual or ground truth information. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge. Additionally, TrustScore can seamlessly integrate with fact-checking methods, which assesses alignment with external knowledge sources. The experimental results show that TrustScore achieves strong correlations with human judgments, surpassing existing reference-free metrics, and achieving results on par with reference-based metrics.
Authors: Shasha Guo, Lizi Liao, Cuiping Li, Tat-Seng Chua
Abstract: In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG's background, encompassing the task's problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed by an in-depth analysis of the distinct neural network models tailored for each category, discussing their inherent strengths and potential limitations. The survey culminates with a forward-looking perspective on the trajectory of NQG, identifying emergent research trends and prospective developmental paths. Accompanying this survey is a curated collection of related research papers, datasets and codes, systematically organized on Github, providing an extensive reference for those delving into NQG.
Authors: Zijie Zeng, Shiqi Liu, Lele Sha, Zhuang Li, Kaixun Yang, Sannyuya Liu, Dragan Ga\v{s}evi\'c, Guanliang Chen
Abstract: This study explores the challenge of sentence-level AI-generated text detection within human-AI collaborative hybrid texts. Existing studies of AI-generated text detection for hybrid texts often rely on synthetic datasets. These typically involve hybrid texts with a limited number of boundaries. We contend that studies of detecting AI-generated content within hybrid texts should cover different types of hybrid texts generated in realistic settings to better inform real-world applications. Therefore, our study utilizes the CoAuthor dataset, which includes diverse, realistic hybrid texts generated through the collaboration between human writers and an intelligent writing system in multi-turn interactions. We adopt a two-step, segmentation-based pipeline: (i) detect segments within a given hybrid text where each segment contains sentences of consistent authorship, and (ii) classify the authorship of each identified segment. Our empirical findings highlight (1) detecting AI-generated sentences in hybrid texts is overall a challenging task because (1.1) human writers' selecting and even editing AI-generated sentences based on personal preferences adds difficulty in identifying the authorship of segments; (1.2) the frequent change of authorship between neighboring sentences within the hybrid text creates difficulties for segment detectors in identifying authorship-consistent segments; (1.3) the short length of text segments within hybrid texts provides limited stylistic cues for reliable authorship determination; (2) before embarking on the detection process, it is beneficial to assess the average length of segments within the hybrid text. This assessment aids in deciding whether (2.1) to employ a text segmentation-based strategy for hybrid texts with longer segments, or (2.2) to adopt a direct sentence-by-sentence classification strategy for those with shorter segments.
Authors: Frances A. Laureano De Leon, Harish Tayyar Madabushi, Mark Lee
Abstract: Code-switching is a prevalent linguistic phenomenon in which multilingual individuals seamlessly alternate between languages. Despite its widespread use online and recent research trends in this area, research in code-switching presents unique challenges, primarily stemming from the scarcity of labelled data and available resources. In this study we investigate how pre-trained Language Models handle code-switched text in three dimensions: a) the ability of PLMs to detect code-switched text, b) variations in the structural information that PLMs utilise to capture code-switched text, and c) the consistency of semantic information representation in code-switched text. To conduct a systematic and controlled evaluation of the language models in question, we create a novel dataset of well-formed naturalistic code-switched text along with parallel translations into the source languages. Our findings reveal that pre-trained language models are effective in generalising to code-switched text, shedding light on the abilities of these models to generalise representations to CS corpora. We release all our code and data including the novel corpus at https://github.com/francesita/code-mixed-probes.
Authors: Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua
Abstract: We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably towards the system's objectives. This poses two main challenges for existing dialogue agents: 1) The inability to integrate user-specific characteristics into the strategic planning, and 2) The difficulty of training strategic planners that can be generalized to diverse users. To address these challenges, we propose Trip to enhance the capability in tailored strategic planning, incorporating a user-aware strategic planning module and a population-based training paradigm. Through experiments on benchmark non-collaborative dialogue tasks, we demonstrate the effectiveness of Trip in catering to diverse users.
Authors: Hongyu Cai, Arjun Arunasalam, Leo Y. Lin, Antonio Bianchi, Z. Berkay Celik
Abstract: Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such alignment can be bypassed to produce prohibited content using a technique commonly referred to as jailbreak. Different systems have been proposed to perform the jailbreak automatically. These systems rely on evaluation methods to determine whether a jailbreak attempt is successful. However, our analysis reveals that current jailbreak evaluation methods have two limitations. (1) Their objectives lack clarity and do not align with the goal of identifying unsafe responses. (2) They oversimplify the jailbreak result as a binary outcome, successful or not. In this paper, we propose three metrics, safeguard violation, informativeness, and relative truthfulness, to evaluate language model jailbreak. Additionally, we demonstrate how these metrics correlate with the goal of different malicious actors. To compute these metrics, we introduce a multifaceted approach that extends the natural language generation evaluation method after preprocessing the response. We evaluate our metrics on a benchmark dataset produced from three malicious intent datasets and three jailbreak systems. The benchmark dataset is labeled by three annotators. We compare our multifaceted approach with three existing jailbreak evaluation methods. Experiments demonstrate that our multifaceted evaluation outperforms existing methods, with F1 scores improving on average by 17% compared to existing baselines. Our findings motivate the need to move away from the binary view of the jailbreak problem and incorporate a more comprehensive evaluation to ensure the safety of the language model.
Authors: Kelvin Wey Han Chan, Christopher Bryant, Li Nguyen, Andrew Caines, Zheng Yuan
Abstract: Code-switching (CSW) is a common phenomenon among multilingual speakers where multiple languages are used in a single discourse or utterance. Mixed language utterances may still contain grammatical errors however, yet most existing Grammar Error Correction (GEC) systems have been trained on monolingual data and not developed with CSW in mind. In this work, we conduct the first exploration into the use of GEC systems on CSW text. Through this exploration, we propose a novel method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora. We then investigate different methods of selecting these spans based on CSW ratio, switch-point factor and linguistic constraints, and identify how they affect the performance of GEC systems on CSW text. Our best model achieves an average increase of 1.57 $F_{0.5}$ across 3 CSW test sets (English-Chinese, English-Korean and English-Japanese) without affecting the model's performance on a monolingual dataset. We furthermore discovered that models trained on one CSW language generalise relatively well to other typologically similar CSW languages.
Authors: Zilong Bai, Ruiji Zhang, Linqing Chen, Qijun Cai, Yuan Zhong, Cong Wang, Yan Fang, Jie Fang, Jing Sun, Weikuan Wang, Lizhi Zhou, Haoran Hua, Tian Qiu, Chaochao Wang, Cheng Sun, Jianping Lu, Yixin Wang, Yubin Xia, Meng Hu, Haowen Liu, Peng Xu, Licong Xu, Fu Bian, Xiaolong Gu, Lisha Zhang, Weilei Wang, Changyang Tu
Abstract: In recent years, large language models(LLMs) have attracted significant attention due to their exceptional performance across a multitude of natural language process tasks, and have been widely applied in various fields. However, the application of large language models in the Intellectual Property (IP) domain is challenging due to the strong need for specialized knowledge, privacy protection, processing of extremely long text in this field. In this technical report, we present for the first time a low-cost, standardized procedure for training IP-oriented LLMs, meeting the unique requirements of the IP domain. Using this standard process, we have trained the PatentGPT series models based on open-source pretrained models. By evaluating them on the open-source IP-oriented benchmark MOZIP, our domain-specific LLMs outperforms GPT-4, indicating the effectiveness of the proposed training procedure and the expertise of the PatentGPT models in the IP domain. Remarkably, our model surpassed GPT-4 on the 2019 China Patent Agent Qualification Examination, scoring 65 and matching human expert levels. Additionally, the PatentGPT model, which utilizes the SMoE architecture, achieves performance comparable to that of GPT-4 in the IP domain and demonstrates a better cost-performance ratio on long-text tasks, potentially serving as an alternative to GPT-4 within the IP domain.
Authors: Wondimagegnhue Tsegaye Tufa, Ilia Markov, Piek Vossen
Abstract: Cross-lingual transfer has become an effective way of transferring knowledge between languages. In this paper, we explore an often overlooked aspect in this domain: the influence of the source language of a language model on language transfer performance. We consider a case where the target language and its script are not part of the pre-trained model. We conduct a series of experiments on monolingual and multilingual models that are pre-trained on different tokenization methods to determine factors that affect cross-lingual transfer to a new language with a unique script. Our findings reveal the importance of the tokenizer as a stronger factor than the shared script, language similarity, and model size.
Authors: Tiziano Labruna, Jon Ander Campos, Gorka Azkune
Abstract: In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to use an off-the-shelf information retrieval (IR) system specifically when additional context is required to answer a given question. Given the performance of IR systems, the optimal strategy for question answering does not always entail external information retrieval; rather, it often involves leveraging the parametric memory of the LLM itself. Prior research has identified this phenomenon in the PopQA dataset, wherein the most popular questions are effectively addressed using the LLM's parametric memory, while less popular ones require IR system usage. Following this, we propose a tailored training approach for LLMs, leveraging existing open-domain question answering datasets. Here, LLMs are trained to generate a special token,
Authors: Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho, He He, Sainbayar Sukhbaatar, Jason Weston
Abstract: Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we develop an iterative approach that optimizes the preference between competing generated Chain-of-Thought (CoT) candidates by optimizing for winning vs. losing reasoning steps that lead to the correct answer. We train using a modified DPO loss (Rafailov et al., 2023) with an additional negative log-likelihood term, which we find to be crucial. We show reasoning improves across repeated iterations of this scheme. While only relying on examples in the training set, our approach results in increasing accuracy on GSM8K, MATH, and ARC-Challenge for Llama-2-70B-Chat, outperforming other Llama-2-based models not relying on additionally sourced datasets. For example, we see a large improvement from 55.6% to 81.6% on GSM8K and an accuracy of 88.7% with majority voting out of 32 samples.
Authors: Tianle Xia, Liang Ding, Guojia Wan, Yibing Zhan, Bo Du, Dacheng Tao
Abstract: Answering complex logical queries over incomplete knowledge graphs (KGs) is challenging. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex logical reasoning schema over knowledge graphs upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements~(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Our code and model will be released at GitHub and huggingface soon.
Authors: Fatema Tuj Johora Faria, Mukaffi Bin Moin, Asif Iftekher Fahim, Pronay Debnath, Faisal Muhammad Shah
Abstract: Natural Language Inference (NLI) is a cornerstone of Natural Language Processing (NLP), providing insights into the entailment relationships between text pairings. It is a critical component of Natural Language Understanding (NLU), demonstrating the ability to extract information from spoken or written interactions. NLI is mainly concerned with determining the entailment relationship between two statements, known as the premise and hypothesis. When the premise logically implies the hypothesis, the pair is labeled "entailment". If the hypothesis contradicts the premise, the pair receives the "contradiction" label. When there is insufficient evidence to establish a connection, the pair is described as "neutral". Despite the success of Large Language Models (LLMs) in various tasks, their effectiveness in NLI remains constrained by issues like low-resource domain accuracy, model overconfidence, and difficulty in capturing human judgment disagreements. This study addresses the underexplored area of evaluating LLMs in low-resourced languages such as Bengali. Through a comprehensive evaluation, we assess the performance of prominent LLMs and state-of-the-art (SOTA) models in Bengali NLP tasks, focusing on natural language inference. Utilizing the XNLI dataset, we conduct zero-shot and few-shot evaluations, comparing LLMs like GPT-3.5 Turbo and Gemini 1.5 Pro with models such as BanglaBERT, Bangla BERT Base, DistilBERT, mBERT, and sahajBERT. Our findings reveal that while LLMs can achieve comparable or superior performance to fine-tuned SOTA models in few-shot scenarios, further research is necessary to enhance our understanding of LLMs in languages with modest resources like Bengali. This study underscores the importance of continued efforts in exploring LLM capabilities across diverse linguistic contexts.
Authors: Yonchanok Khaokaew, Kaixin Ji, Thuc Hanh Nguyen, Hiruni Kegalle, Marwah Alaofi, Hao Xue, Flora D. Salim
Abstract: This paper explores the intersection of technology and sleep pattern comprehension, presenting a cutting-edge two-stage framework that harnesses the power of Large Language Models (LLMs). The primary objective is to deliver precise sleep predictions paired with actionable feedback, addressing the limitations of existing solutions. This innovative approach involves leveraging the GLOBEM dataset alongside synthetic data generated by LLMs. The results highlight significant improvements, underlining the efficacy of merging advanced machine-learning techniques with a user-centric design ethos. Through this exploration, we bridge the gap between technological sophistication and user-friendly design, ensuring that our framework yields accurate predictions and translates them into actionable insights.
Authors: Lena Strobl, William Merrill, Gail Weiss, David Chiang, Dana Angluin
Abstract: As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help clarify the power of transformers relative to other models of computation, their fundamental capabilities and limits, and the impact of architectural choices. Work in this subarea has made considerable progress in recent years. Here, we undertake a comprehensive survey of this work, documenting the diverse assumptions that underlie different results and providing a unified framework for harmonizing seemingly contradictory findings.
Authors: Shuyang Sun, Runjia Li, Philip Torr, Xiuye Gu, Siyang Li
Abstract: Existing open-vocabulary image segmentation methods require a fine-tuning step on mask labels and/or image-text datasets. Mask labels are labor-intensive, which limits the number of categories in segmentation datasets. Consequently, the vocabulary capacity of pre-trained VLMs is severely reduced after fine-tuning. However, without fine-tuning, VLMs trained under weak image-text supervision tend to make suboptimal mask predictions. To alleviate these issues, we introduce a novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training efforts. The recurrent unit is a two-stage segmenter built upon a frozen VLM. Thus, our model retains the VLM's broad vocabulary space and equips it with segmentation ability. Experiments show that our method outperforms not only the training-free counterparts, but also those fine-tuned with millions of data samples, and sets the new state-of-the-art records for both zero-shot semantic and referring segmentation. Concretely, we improve the current record by 28.8, 16.0, and 6.9 mIoU on Pascal VOC, COCO Object, and Pascal Context.
Authors: Madeleine Grunde-McLaughlin, Michelle S. Lam, Ranjay Krishna, Daniel S. Weld, Jeffrey Heer
Abstract: LLM chains enable complex tasks by decomposing work into a sequence of subtasks. Similarly, the more established techniques of crowdsourcing workflows decompose complex tasks into smaller tasks for human crowdworkers. Chains address LLM errors analogously to the way crowdsourcing workflows address human error. To characterize opportunities for LLM chaining, we survey 107 papers across the crowdsourcing and chaining literature to construct a design space for chain development. The design space covers a designer's objectives and the tactics used to build workflows. We then surface strategies that mediate how workflows use tactics to achieve objectives. To explore how techniques from crowdsourcing may apply to chaining, we adapt crowdsourcing workflows to implement LLM chains across three case studies: creating a taxonomy, shortening text, and writing a short story. From the design space and our case studies, we identify takeaways for effective chain design and raise implications for future research and development.
Authors: Zongbo Han, Zechen Bai, Haiyang Mei, Qianli Xu, Changqing Zhang, Mike Zheng Shou
Abstract: Recent advancements in large vision-language models (LVLMs) have demonstrated impressive capability in visual information understanding with human language. Despite these advances, LVLMs still face challenges with multimodal hallucination, such as generating text descriptions of objects that are not present in the visual information. However, the underlying fundamental reasons of multimodal hallucinations remain poorly explored. In this paper, we propose a new perspective, suggesting that the inherent biases in LVLMs might be a key factor in hallucinations. Specifically, we systematically identify a semantic shift bias related to paragraph breaks (\n\n), where the content before and after '\n\n' in the training data frequently exhibit significant semantic changes. This pattern leads the model to infer that the contents following '\n\n' should be obviously different from the preceding contents with less hallucinatory descriptions, thereby increasing the probability of hallucinatory descriptions subsequent to the '\n\n'. We have validated this hypothesis on multiple publicly available LVLMs. Besides, we find that deliberately inserting '\n\n' at the generated description can induce more hallucinations. A simple method is proposed to effectively mitigate the hallucination of LVLMs by skipping the output of '\n'.
Authors: Jennifer Chien, David Danks
Abstract: Algorithmic harms are commonly categorized as either allocative or representational. This study specifically addresses the latter, focusing on an examination of current definitions of representational harms to discern what is included and what is not. This analysis motivates our expansion beyond behavioral definitions to encompass harms to cognitive and affective states. The paper outlines high-level requirements for measurement: identifying the necessary expertise to implement this approach and illustrating it through a case study. Our work highlights the unique vulnerabilities of large language models to perpetrating representational harms, particularly when these harms go unmeasured and unmitigated. The work concludes by presenting proposed mitigations and delineating when to employ them. The overarching aim of this research is to establish a framework for broadening the definition of representational harms and to translate insights from fairness research into practical measurement and mitigation praxis.
Authors: Xiyuan Zhang, Ranak Roy Chowdhury, Rajesh K. Gupta, Jingbo Shang
Abstract: Large Language Models (LLMs) have seen significant use in domains such as natural language processing and computer vision. Going beyond text, image and graphics, LLMs present a significant potential for analysis of time series data, benefiting domains such as climate, IoT, healthcare, traffic, audio and finance. This survey paper provides an in-depth exploration and a detailed taxonomy of the various methodologies employed to harness the power of LLMs for time series analysis. We address the inherent challenge of bridging the gap between LLMs' original text data training and the numerical nature of time series data, and explore strategies for transferring and distilling knowledge from LLMs to numerical time series analysis. We detail various methodologies, including (1) direct prompting of LLMs, (2) time series quantization, (3) aligning techniques, (4) utilization of the vision modality as a bridging mechanism, and (5) the combination of LLMs with tools. Additionally, this survey offers a comprehensive overview of the existing multimodal time series and text datasets and delves into the challenges and future opportunities of this emerging field. We maintain an up-to-date Github repository which includes all the papers and datasets discussed in the survey.
Authors: Wasu Top Piriyakulkij, Kevin Ellis
Abstract: We build a computational model of how humans actively infer hidden rules by doing experiments. The basic principles behind the model is that, even if the rule is deterministic, the learner considers a broader space of fuzzy probabilistic rules, which it represents in natural language, and updates its hypotheses online after each experiment according to approximately Bayesian principles. In the same framework we also model experiment design according to information-theoretic criteria. We find that the combination of these three principles -- explicit hypotheses, probabilistic rules, and online updates -- can explain human performance on a Zendo-style task, and that removing any of these components leaves the model unable to account for the data.
Authors: Qiuyu Liang, Weihua Wang, Feilong Bao, Guanglai Gao
Abstract: Linear Graph Convolutional Networks (GCNs) are used to classify the node in the graph data. However, we note that most existing linear GCN models perform neural network operations in Euclidean space, which do not explicitly capture the tree-like hierarchical structure exhibited in real-world datasets that modeled as graphs. In this paper, we attempt to introduce hyperbolic space into linear GCN and propose a novel framework for Lorentzian linear GCN. Specifically, we map the learned features of graph nodes into hyperbolic space, and then perform a Lorentzian linear feature transformation to capture the underlying tree-like structure of data. Experimental results on standard citation networks datasets with semi-supervised learning show that our approach yields new state-of-the-art results of accuracy 74.7$\%$ on Citeseer and 81.3$\%$ on PubMed datasets. Furthermore, we observe that our approach can be trained up to two orders of magnitude faster than other nonlinear GCN models on PubMed dataset. Our code is publicly available at https://github.com/llqy123/LLGC-master.
Authors: Orion Weller, Benjamin Chang, Sean MacAvaney, Kyle Lo, Arman Cohan, Benjamin Van Durme, Dawn Lawrie, Luca Soldaini
Abstract: Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures, virtually none of them allow users to provide detailed instructions alongside queries, thus limiting their ability to satisfy complex information needs. In this work, we study the use of instructions in IR systems. First, we introduce our dataset FollowIR, which contains a rigorous instruction evaluation benchmark as well as a training set for helping IR models learn to better follow real-world instructions. FollowIR repurposes detailed instructions -- also known as narratives -- developed for professional assessors to evaluate retrieval systems. In particular, we build our benchmark from three collections curated for shared tasks at the Text REtrieval Conference (TREC). These collections contains hundreds to thousands of labeled documents per query, making them suitable for our exploration. Through this process, we can measure how well IR models follow instructions, through a new pairwise evaluation framework. Our results indicate that existing retrieval models fail to correctly use instructions, using them for basic keywords and struggling to understand long-form information. However, we show that it is possible for IR models to learn to follow complex instructions: our new FollowIR-7B model has significant improvements after fine-tuning on our training set.
Authors: Hao Chen, Minyu Chen, Ruibang Liu, Guoqiang Li, Sinka Gao
Abstract: ZKP systems have surged attention and held a fundamental role in contemporary cryptography. Zk-SNARK protocols dominate the ZKP usage, often implemented through arithmetic circuit programming paradigm. However, underconstrained or overconstrained circuits may lead to bugs. Underconstrained circuits refer to circuits that lack the necessary constraints, resulting in unexpected solutions in the circuit and causing the verifier to accept a bogus witness. Overconstrained circuits refer to circuits that are constrained excessively, resulting in the circuit lacking necessary solutions and causing the verifier to accept no witness, rendering the circuit meaningless. This paper introduces a novel approach for pinpointing two distinct types of bugs in ZKP circuits. The method involves encoding the arithmetic circuit constraints to polynomial equation systems and solving polynomial equation systems over a finite field by algebraic computation. The classification of verification results is refined, greatly enhancing the expressive power of the system. We proposed a tool, AC4, to represent the implementation of this method. Experiments demonstrate that AC4 represents a substantial 29% increase in the checked ratio compared to prior work. Within a solvable range, the checking time of AC4 has also exhibited noticeable improvement, demonstrating a magnitude increase compared to previous efforts.
Authors: Uri Hacohen, Adi Haviv, Shahar Sarfaty, Bruria Friedman, Niva Elkin-Koren, Roi Livni, Amit H Bermano
Abstract: The advent of Generative Artificial Intelligence (GenAI) models, including GitHub Copilot, OpenAI GPT, and Stable Diffusion, has revolutionized content creation, enabling non-professionals to produce high-quality content across various domains. This transformative technology has led to a surge of synthetic content and sparked legal disputes over copyright infringement. To address these challenges, this paper introduces a novel approach that leverages the learning capacity of GenAI models for copyright legal analysis, demonstrated with GPT2 and Stable Diffusion models. Copyright law distinguishes between original expressions and generic ones (Sc\`enes \`a faire), protecting the former and permitting reproduction of the latter. However, this distinction has historically been challenging to make consistently, leading to over-protection of copyrighted works. GenAI offers an unprecedented opportunity to enhance this legal analysis by revealing shared patterns in preexisting works. We propose a data-driven approach to identify the genericity of works created by GenAI, employing "data-driven bias" to assess the genericity of expressive compositions. This approach aids in copyright scope determination by utilizing the capabilities of GenAI to identify and prioritize expressive elements and rank them according to their frequency in the model's dataset. The potential implications of measuring expressive genericity for copyright law are profound. Such scoring could assist courts in determining copyright scope during litigation, inform the registration practices of Copyright Offices, allowing registration of only highly original synthetic works, and help copyright owners signal the value of their works and facilitate fairer licensing deals. More generally, this approach offers valuable insights to policymakers grappling with adapting copyright law to the challenges posed by the era of GenAI.
Authors: Dongseong Hwang, Weiran Wang, Zhuoyuan Huo, Khe Chai Sim, Pedro Moreno Mengibar
Abstract: While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages a feedback loop to enable the network to attend to its own latent representations. This design fosters the emergence of working memory within the Transformer, allowing it to process indefinitely long sequences. TransformerFAM requires no additional weights, enabling seamless integration with pre-trained models. Our experiments show that TransformerFAM significantly improves Transformer performance on long-context tasks across various model sizes (1B, 8B, and 24B). These results showcase the potential to empower Large Language Models (LLMs) to process sequences of unlimited length.
Authors: Jairo Gudi\~no-Rosero, Umberto Grandi, C\'esar A. Hidalgo
Abstract: We explore the capabilities of an augmented democracy system built on off-the-shelf LLMs fine-tuned on data summarizing individual preferences across 67 policy proposals collected during the 2022 Brazilian presidential elections. We use a train-test cross-validation setup to estimate the accuracy with which the LLMs predict both: a subject's individual political choices and the aggregate preferences of the full sample of participants. At the individual level, the accuracy of the out of sample predictions lie in the range 69%-76% and are significantly better at predicting the preferences of liberal and college educated participants. At the population level, we aggregate preferences using an adaptation of the Borda score and compare the ranking of policy proposals obtained from a probabilistic sample of participants and from data augmented using LLMs. We find that the augmented data predicts the preferences of the full population of participants better than probabilistic samples alone when these represent less than 30% to 40% of the total population. These results indicate that LLMs are potentially useful for the construction of systems of augmented democracy.