论文检索

Sudipta Singha Roy, Xindi Wang, Robert Mercer, Frank Rudzicz

Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchical relationships within documents. To address these constraints, we propose a novel model leveraging a graph-tree structure. Our approach integrates syntax trees for sentence encodings and document graphs for document encodings, which capture fine-grained syntactic relationships and broader document contexts, respectively. We use Tree Transformers to generate sentence encodings, while a graph attention network models inter- and intra-sentence dependencies. During training, we implement bidirectional information propagation from word-to-sentence-to-document and vice versa, which enriches the contextual representation. Our proposed method enables a comprehensive understanding of content at all hierarchical levels and effectively handles arbitrarily long contexts without token limit constraints. Experimental results demonstrate the effectiveness of our approach in all types of long document classification tasks.

Qizhi Wan, Changxuan Wan, Rong Hu, Dexi Liu, Xu Wenwu, Kang Xu, Zou Meihua, Liu Tao, Jie Yang, Zhenwei Xiong

To meet application needs, event extraction has shifted from simple entities to unconventional entities serving as event arguments. However, current corpora with unconventional entities as event arguments are limited in event types and lack rich multi-events and shared arguments. Financial commentary not only describes the basic elements of an event but also states the background, scope, manner, condition, result, and tool used for the event, as well as the tense, intensity, and emotions of actions or state changes. Therefore, it is not suitable to develop event types that include only a few specific roles, as these cannot comprehensively capture the event’s semantics. Also, there are affluent complex entities serving as event arguments, multiple events, and shared event arguments. To advance the practicality of event extraction technology, this paper first develops a general open event template from the perspective of understanding the meaning of events, aiming to comprehensively reveal useful information about events. This template includes 21 event argument roles, divided into three categories: core event roles, situational event roles, and adverbial roles. Then, based on the constructed event template, Chinese financial commentaries are collected and manually annotated to create a corpus OEE-CFC supporting open event extraction. This corpus includes 17,469 events, 44,221 arguments, 3,644 complex arguments, and 5,898 shared arguments. Finally, based on the characteristics of OEE-CFC, we design four types of prompts, and two models for event argument extraction are developed, with experiments conducted on the prompts.

Filip Trhlík, Pontus Stenetorp

Large language models (LLMs) are increasingly being utilised across a range of tasks and domains, with a burgeoning interest in their application within the field of journalism. This trend raises concerns due to our limited understanding of LLM behaviour in this domain, especially with respect to political bias. Existing studies predominantly focus on LLMs undertaking political questionnaires, which offers only limited insights into their biases and operational nuances. To address this gap, our study establishes a new curated dataset that contains 2,100 human-written articles and utilises their descriptions to generate 56,700 synthetic articles using nine LLMs. This enables us to analyse shifts in properties between human-authored and machine-generated articles, with this study focusing on political bias, detecting it using both supervised models and LLMs. Our findings reveal significant disparities between base and instruction-tuned LLMs, with instruction-tuned models exhibiting consistent political bias. Furthermore, we are able to study how LLMs behave as classifiers, observing their display of political bias even in this role. Overall, for the first time within the journalistic domain, this study outlines a framework and provides a structured dataset for quantifiable experiments, serving as a foundation for further research into LLM political bias and its implications.

Ming Shan Hee, Shivam Sharma, Rui Cao, Palash Nandi, Preslav Nakov, Tanmoy Chakraborty, Roy Ka-Wei Lee

Moderating hate speech (HS) in the evolving online landscape is a complex challenge, compounded by the multimodal nature of digital content. This survey examines recent advancements in HS moderation, focusing on the burgeoning role of large language models (LLMs) and large multimodal models (LMMs) in detecting, explaining, debiasing, and countering HS. We begin with a comprehensive analysis of current literature, uncovering how text, images, and audio interact to spread HS. The combination of these modalities adds complexity and subtlety to HS dissemination. We also identified research gaps, particularly in underrepresented languages and cultures, and highlight the need for solutions in low-resource settings. The survey concludes with future research directions, including novel AI methodologies, ethical AI governance, and the development of context-aware systems. This overview aims to inspire further research and foster collaboration towards responsible and human-centric approaches to HS moderation in the digital age.

Zirui Wu, Yansong Feng

Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. The framework first plans the reasoning paths over the context, then assigns each step to program-based or textual reasoning to reach the final answer. This framework enhances the table reasoning abilities for both in-context learning and fine-tuning methods. GPT-3.5-Turbo following Plan-then-Reason framework surpasses other prompting baselines without self-consistency while using less API calls and in-context demonstrations. We also construct an instruction tuning set TrixInstruct to evaluate the effectiveness of fine-tuning with this framework. We present ProTrix model family by finetuning models on TrixInstruct. Our experiments show that ProTrix family generalizes to diverse unseen tabular tasks with only 6k training instances. We further demonstrate that ProTrix can generate accurate and faithful explanations to answer complex free-form questions. Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability. We will open-source our dataset and models.

Xuanwen Ding, Jie Zhou, Liang Dou, Qin Chen, Yuanbin Wu, Arlene Chen, Liang He

Aspect-based sentiment analysis (ABSA) is an important subtask of sentiment analysis, which aims to extract the aspects and predict their sentiments. Most existing studies focus on improving the performance of the target domain by fine-tuning domain-specific models (trained on source domains) based on the target domain dataset. Few works propose continual learning tasks for ABSA, which aim to learn the target domain’s ability while maintaining the history domains’ abilities. In this paper, we propose a Large Language Model-based Continual Learning (LLM-CL) model for ABSA. First, we design a domain knowledge decoupling module to learn a domain-invariant adapter and separate domain-variant adapters dependently with an orthogonal constraint. Then, we introduce a domain knowledge warmup strategy to align the representation between domain-invariant and domain-variant knowledge. In the test phase, we index the corresponding domain-variant knowledge via domain positioning to not require each sample’s domain ID. Extensive experiments over 19 datasets indicate that our LLM-CL model obtains new state-of-the-art performance.

Flor Miriam Plaza-del-Arco, Amanda Cercas Curry, Susanna Paoli, Alba Cercas Curry, Dirk Hovy

Emotions play important epistemological and cognitive roles in our lives, revealing our values and guiding our actions. Previous work has shown that LLMs display biases in emotion attribution along gender lines. However, unlike gender, which says little about our values, religion, as a socio-cultural system, prescribes a set of beliefs and values for its followers. Religions, therefore, cultivate certain emotions. Moreover, these rules are explicitly laid out and interpreted by religious leaders. Using emotion attribution, we explore how different religions are represented in LLMs. We find that:Major religions in the US and European countries are represented with more nuance, displaying a more shaded model of their beliefs.Eastern religions like Hinduism and Buddhism are strongly stereotyped.Judaism and Islam are stigmatized – the models’ refusal skyrocket. We ascribe these to cultural bias in LLMs and the scarcity of NLP literature on religion. In the rare instances where religion is discussed, it is often in the context of toxic language, perpetuating the perception of these religions as inherently toxic. This finding underscores the urgent need to address and rectify these biases. Our research emphasizes the crucial role emotions play in shaping our lives and how our values influence them.

Florian Schneider, Sunayana Sitaram

Since the release of ChatGPT, the field of Natural Language Processing has experienced rapid advancements, particularly in Large Language Models (LLMs) and their multimodal counterparts, Large Multimodal Models (LMMs). Despite their impressive capabilities, LLMs often exhibit significant performance disparities across different languages and cultural contexts, as demonstrated by various text-only benchmarks. However, current research lacks such benchmarks for multimodal visio-linguistic settings. This work fills this gap by introducing M5, the first comprehensive benchmark designed to evaluate LMMs on diverse vision-language tasks within a multilingual and multicultural context. M5 includes eight datasets covering five tasks and 41 languages, with a focus on underrepresented languages and culturally diverse images. Furthermore, we introduce two novel datasets, M5-VGR and M5-VLOD, including a new Visio-Linguistic Outlier Detection task, in which all evaluated open-source models fail to significantly surpass the random baseline. Through extensive evaluation and analyses, we highlight substantial task-agnostic performance disparities between high- and low-resource languages. Moreover, we show that larger models do not necessarily outperform smaller ones in a multilingual setting.

Hongyu Li, Liang Ding, Meng Fang, Dacheng Tao

Catastrophic Forgetting (CF) means models forgetting previously acquired knowledge when learning new data. It compromises the effectiveness of large language models (LLMs) during fine-tuning, yet the underlying causes have not been thoroughly investigated. This paper takes the first step to reveal the direct link between the flatness of the model loss landscape and the extent of CF in the field of LLMs. Based on this, we introduce the sharpness-aware minimization to mitigate CF by flattening the loss landscape. Experiments on three widely-used fine-tuning datasets, spanning different model scales, demonstrate the effectiveness of our method in alleviating CF. Analyses show that we nicely complement the existing anti-forgetting strategies, further enhancing the resistance of LLMs to CF.

Tim Hagen, Harrisen Scells, Martin Potthast

The most commonly used transformers for retrieval at present, BERT and T5, have been shown not to be robust to query variations such as typos or paraphrases. Although this is an important prerequisite for their practicality, this problem has hardly been investigated. More recent large language models (LLMs), including instruction-tuned LLMs, have not been analyzed yet, and only one study looks beyond typos. We close this gap by reproducing this study and extending it with a systematic analysis of more recent models, including Sentence-BERT, CharacterBERT, E5-Mistral, AnglE, and Ada v2. We further investigate if instruct-LLMs can be prompted for robustness. Our results are mixed in that the previously observed robustness issues for cross-encoders also apply to bi-encoders that use much larger LLMs, albeit to a lesser extent. While further LLM scaling may improve their embeddings, their cost-effective use for all but large deployments is limited. Training data that includes query variations allows LLMs to be fine-tuned for more robustness, but focusing on a single category of query variation may even degrade the effectiveness on others. Our code, results, and artifacts can be found at https://github.com/webis-de/EMNLP-24

Peixin Qin, Chen Huang, Yang Deng, Wenqiang Lei, Tat-Seng Chua

With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items. While these CRSs are highly persuasive, they can mislead users by incorporating incredible information in their explanations, ultimately damaging the long-term trust between users and the CRS. To address this, we propose a simple yet effective method, called PC-CRS, to enhance the credibility of CRS’s explanations during persuasion. It guides the explanation generation through our proposed credibility-aware persuasive strategies and then gradually refines explanations via post-hoc self-reflection. Experimental results demonstrate the efficacy of PC-CRS in promoting persuasive and credible explanations. Further analysis reveals the reason behind current methods producing incredible explanations and the potential of credible explanations to improve recommendation accuracy.

Jianyi Chen, Zheqi Dai, Zhen Ye, Xu Tan, Qifeng Liu, Yike Guo, Wei Xue

Generating well-structured long music compositions, spanning several minutes, remains a challenge due to inefficient representation and the lack of structured representation. In this paper, we propose PyramidCodec, a hierarchical discrete representation of audio, for long audio-domain music generation. Specifically, we employ residual vector quantization on different levels of features to obtain the hierarchical discrete representation. The highest level of features has the largest hop size, resulting in the most compact token sequence. The quantized higher-level representation is up-sampled and combined with lower-level features to apply residual vector quantization and obtain lower-level discrete representations. Furthermore, we design a hierarchical training strategy to ensure that the details are gradually added with more levels of tokens. By performing hierarchical tokenization, the overall token sequence represents information at various scales, facilitating long-context modeling in music and enabling the generation of well-structured compositions. The experimental results demonstrate that our proposed PyramidCodec achieves competitive performance in terms of reconstruction quality and token per second (TPS). By enabling ultra-long music modeling at the lowest level, the proposed approach facilitates training a language model that can generate well-structured long-form music for up to 3 minutes, whose quality is further demonstrated by subjective and objective evaluations. The samples can be found at https://pyramidcodec.github.io/.

Lingyun Song, Chengkun Yang, Xuanyu Li, Xuequn Shang

Traditional VQA models are inherently vulnerable to language bias, resulting in a significant performance drop when encountering out-of-distribution datasets. The conventional VQA models suffer from language bias that indicates a spurious correlation between textual questions and answers. Given the outstanding effectiveness of counterfactual causal inference in eliminating bias, we propose a model agnostic dual-debiasing framework based on Counterfactual Causal Effect (DCCE), which explicitly models two types of language bias(i.e., shortcut and distribution bias) by separate branches under the counterfactual inference framework. The effects of both types ofbias on answer prediction can be effectively mitigated by subtracting direct effect of textual questions on answers from total effect ofvisual questions on answers. Experimental results demonstrate that our proposed DCCE framework significantly reduces language biasand achieves state-of-the-art performance on the benchmark datasets without requiring additional augmented data. Our code is available inhttps://github.com/sxycyck/dcce.

Chunkit Chan, Cheng Jiayang, Yauwai Yim, Zheye Deng, Wei Fan, Haoran Li, Xin Liu, Hongming Zhang, Weiqi Wang, Yangqiu Song

Large Language Models (LLMs) have sparked substantial interest and debate concerning their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations currently focuses on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations, which lacks evaluation of machine ToM ability in real-world human interaction scenarios. This poses a pressing demand to develop new real-world scenario benchmarks. We introduce NegotiationToM, a new benchmark designed to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states (i.e., desires, beliefs, and intentions). Our benchmark builds upon the Belief-Desire-Intention (BDI) agent modeling theory and conducts the necessary empirical experiments to evaluate large language models. Our findings demonstrate that NegotiationToM is challenging for state-of-the-art LLMs, as they consistently perform significantly worse than humans, even when employing the chain-of-thought (CoT) method.

Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin

Classical Chinese is a gateway to the rich heritage and wisdom of ancient China, yet its complexities pose formidable comprehension barriers for most modern people without specialized knowledge. While Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), they struggle with Classical Chinese Understanding (CCU), especially in data-demanding and knowledge-intensive tasks. In response to this dilemma, we propose TongGu (mean understanding ancient and modern), the first CCU-specific LLM, underpinned by three core contributions. First, we construct a two-stage instruction-tuning dataset ACCN-INS derived from rich classical Chinese corpora, aiming to unlock the full CCU potential of LLMs. Second, we propose Redundancy-Aware Tuning (RAT) to prevent catastrophic forgetting, enabling TongGu to acquire new capabilities while preserving its foundational knowledge. Third, we present a CCU Retrieval-Augmented Generation (CCU-RAG) technique to reduce hallucinations based on knowledge-grounding. Extensive experiments across 24 diverse CCU tasks validate TongGu’s superior ability, underscoring the effectiveness of RAT and CCU-RAG. The model and dataset are available at https://github.com/SCUT-DLVCLab/TongGu-LLM.

Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang, Chao Yang, Yu Qiao

Large language models are typically fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. In this work, we introduce **Integrated Value Guidance (IVG)**, a method that uses implicit and explicit value functions to guide language model decoding at token and chunk-level respectively, efficiently aligning large language models purely at inference time.This approach circumvents the complexities of direct fine-tuning and outperforms traditional methods.Empirically, we demonstrate the versatility of IVG across various tasks. In controlled sentiment generation and summarization tasks, our method significantly improves the alignment of large models using inference-time guidance from **gpt2**-based value functions. Moreover, in a more challenging instruction-following benchmark AlpacaEval 2.0, we show that both specifically tuned and off-the-shelf value functions greatly improve the length-controlled win rates of large models against gpt-4-turbo (e.g., 19.51 % \rightarrow 26.51\% for **Mistral-7B-Instruct-v0.2** and 25.58 % \rightarrow 33.75 \% for **Mixtral-8x7B-Instruct-v0.1** with Tulu guidance).

Hayoon Kim, Ahyeon Choi, Sungho Lee, Hyun Jin Jung, Kyogu Lee

This paper presents Emosical, a multimodal open-source dataset of musical films. Emosical comprises video, vocal audio, text, and character identity paired samples with annotated emotion tags. Emosical provides rich emotion annotations for each sample by inferring the background story of the characters. To achieve this, we leverage the musical theatre script, which contains the characters’ complete background stories and narrative contexts. The annotation pipeline includes feeding the speaking character, text, global persona, and context of the dialogue and song track into a large language model. To verify the effectiveness of our tagging scheme, we perform an ablation study by bypassing each step of the pipeline. The ablation results show the usefulness of each component in generating accurate emotion tags. A subjective test is conducted to compare the generated tags of each ablation result. We also perform a statistical analysis to find out the global characteristics of the collected emotion tags. Emosical would enable expressive synthesis and tagging of the speech and singing voice in the musical theatre domain in future research. Emosical is publicly available at https://github.com/gillosae/emosical.

Yixin Ji, Yang Xiang, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Kehai Chen, Min Zhang

In recent years, large language models (LLMs) have driven advances in natural language processing. Still, their growing scale has increased the computational burden, necessitating a balance between efficiency and performance. Low-rank compression, a promising technique, reduces non-essential parameters by decomposing weight matrices into products of two low-rank matrices. Yet, its application in LLMs has not been extensively studied. The key to low-rank compression lies in low-rank factorization and low-rank dimensions allocation. To address the challenges of low-rank compression in LLMs, we conduct empirical research on the low-rank characteristics of large models. We propose a low-rank compression method suitable for LLMs. This approach involves precise estimation of feature distributions through pooled covariance matrices and a Bayesian optimization strategy for allocating low-rank dimensions. Experiments on the LLaMA-2 models demonstrate that our method outperforms existing strong structured pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

Qingyu Yin, Xuzheng He, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang

Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surpass ICL given sufficient training samples as it allows the model to adjust its internal parameters based on the data. However, this paper presents a counterintuitive finding: For tasks with implicit patterns, ICL captures these patterns significantly better than fine-tuning. We developed several datasets featuring implicit patterns, such as sequences determining answers through parity or identifying reducible terms in calculations. We then evaluated the models’ understanding of these patterns under both fine-tuning and ICL across models ranging from 0.5B to 7B parameters. The results indicate that models employing ICL can quickly grasp deep patterns and significantly improve accuracy. In contrast, fine-tuning, despite utilizing thousands of times more training samples than ICL, achieved only limited improvements. We also proposed circuit shift theory from a mechanistic interpretability’s view to explain why ICL wins.

Ruijun Chen, Jiehao Liang, Shiping Gao, Fanqi Wan, Xiaojun Quan

The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. To address the challenges of current alignment methodologies, we introduce self-evolution fine-tuning (SEFT) for LLM alignment, aiming to eliminate the need for annotated samples while retaining the stability and efficiency of SFT. SEFT first trains an adaptive reviser to elevate low-quality responses while maintaining high-quality ones. The reviser then gradually guides the policy’s optimization by fine-tuning it with enhanced responses. The method excels in utilizing unlimited unannotated data to optimize policies via supervised fine-tuning. Our experiments on AlpacaEval and MT-Bench demonstrate the effectiveness of SEFT and its advantages over existing alignment techniques.