论文检索

Jae-Woo Park, Seong-Jin Park, Hyun-Sik Won, Kang-Min Kim

Recent advancements in educational platforms have emphasized the importance of personalized education. Accurately estimating question difficulty based on the ability of the student group is essential for personalized question recommendations. Several studies have focused on predicting question difficulty using student question-solving records or textual information about the questions. However, these approaches require a large amount of student question-solving records and fail to account for the subjective difficulties perceived by different student groups. To address these limitations, we propose the LLaSA framework that utilizes large language models to represent students at various levels. Our proposed method, LLaSA and the zero-shot LLaSA, can estimate question difficulty both with and without students’ question-solving records. In evaluations on the DBE-KT22 and ASSISTMents 2005–2006 benchmarks, the zero-shot LLaSA demonstrated a performance comparable to those of strong baseline models even without any training. When evaluated using the classification method, LLaSA outperformed the baseline models, achieving state-of-the-art performance. In addition, the zero-shot LLaSA showed a high correlation with the regressed IRT curve when compared to question difficulty derived from students’ question-solving records, highlighting its potential for real-world applications.

Yuncheng Hua, Yujin Huang, Shuo Huang, Tao Feng, Lizhen Qu, Christopher Bain, Richard Bassed, Reza Haf

This paper tackles the task of emotion-cause pair extraction in the unsupervised domain adaptation setting.The problem is challenging as the distributions of the events causing emotions in target domains are dramatically different than those in source domains, despite the distributions of emotional expressions between domains are overlapped. Inspired by causal discovery,we propose a novel deep latent model in the variational autoencoder (VAE) framework, which not only captures the underlying latent structures of data but also utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different domains. To facilitate knowledge transfer across domains, we also propose a novel variational posterior regularization technique to disentangle the latent representations of emotions from those of events in order to mitigate the damage caused by the spurious correlations related to the events in source domains. Through extensive experiments, we demonstrate that our model outperforms the strongest baseline by approximately 11.05% on a Chinese benchmark and 2.45% on a English benchmark in terms of weighted-average F1 score. We have released our source code and the generated dataset publicly at: https://github.com/tk1363704/CAREL-VAE.

Linyan Yang, Jingwei Cheng, Fu Zhang

In recent years, the advent of large language models (LLMs) like GPT and Llama has significantly influenced numerous domains, particularly in advancing natural language processing (NLP) capabilities. LLMs have shown remarkable performance in NLP tasks such as relation extraction (RE) and knowledge graph completion (KGC), enhancing activities related to knowledge graphs. As a result, there is a growing interest in integrating LLMs into cross-lingual entity alignment (EA) task, which aims to identify equivalent entities across various knowledge graphs, thereby improving the performance of current baselines. However, employing LLMs for entity alignment poses challenges in efficiently handling large-scale data, generating suitable data samples, and adapting prompts for the EA task. To tackle these challenges, we propose Seg-Align, an innovative framework that integrating distance feature extraction, sample **Seg**mentation, and zero-shot prompts. Through extensive experiments on two widely used cross-lingual benchmark datasets, we have not only demonstrated the effectiveness of our proposed sample segmentation algorithm but also highlighted the state-of-the-art performance of Seg-Align. Code is available at https://github.com/yangxiaoxiaoly/Seg-Align.

Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang 等

Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in natural language processing. In particular, large language models (LLMs) can hardly produce written works at the level of human experts due to the extremely high complexity of literature writing. In this paper, we present HoLLMwood, an automated framework for unleashing the creativity of LLMs and exploring their potential in screenwriting, which is a highly demanding task. Mimicking the human creative process, we assign LLMs to different roles involved in the real-world scenario. In addition to the common practice of treating LLMs as Writer, we also apply LLMs as Editor, who is responsible for providing feedback and revision advice to Writer. Besides, to enrich the characters and deepen the plots, we introduce a role-playing mechanism and adopt LLMs as Actors that can communicate and interact with each other. Evaluations on automatically generated screenplays show that HoLLMwood substantially outperforms strong baselines in terms of coherence, relevance, interestingness and overall quality.

Yuncheng Hua, Lizhen Qu, Reza Haf

We develop assistive agents based on Large Language Models (LLMs) that aid interlocutors in business negotiations.Specifically, we simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes.We introduce a simple tuning-free and label-free In-Context Learning (ICL) method to identify high-quality ICL exemplars for the remediator, where we propose a novel select criteria, called value impact, to measure the quality of the negotiation outcomes. We provide rich empirical evidence to demonstrate its effectiveness in negotiations across three different negotiation topics. We have released our source code and the generated dataset at: https://github.com/tk1363704/SADAS.

Huifang Du, Shuqin Li, Minghao Wu, Xuejing Feng, Yuan-Fang Li, Haofen Wang

Reinforcement learning (RL) is a powerful approach to enhance task-oriented dialogue (TOD) systems. However, existing RL methods tend to mainly focus on generation tasks, such as dialogue policy learning (DPL) or response generation (RG), while neglecting dialogue state tracking (DST) for understanding. This narrow focus limits the systems to achieve globally optimal performance by overlooking the interdependence between understanding and generation. Additionally, RL methods face challenges with sparse and delayed rewards, which complicates training and optimization. To address these issues, we extend RL into both understanding and generation tasks by introducing step-by-step rewards throughout the token generation. The understanding reward increases as more slots are correctly filled in DST, while the generation reward grows with the accurate inclusion of user requests. Our approach provides a balanced optimization aligned with task completion. Experimental results demonstrate that our approach effectively enhances the performance of TOD systems and achieves new state-of-the-art results on three widely used datasets, including MultiWOZ2.0, MultiWOZ2.1, and In-Car. Our approach also shows superior few-shot ability in low-resource settings compared to current models.

Seyed Mahed Mousavi, Simone Alghisi, Giuseppe Riccardi

LLMs acquire knowledge from massive data snapshots collected at different timestamps. Their knowledge is then commonly evaluated using static benchmarks. However, factual knowledge is generally subject to time-sensitive changes, and static benchmarks cannot address those cases. We present an approach to dynamically evaluate the knowledge in LLMs and their time-sensitiveness against Wikidata, a publicly available up-to-date knowledge graph. We evaluate the time-sensitive knowledge in twenty-four private and open-source LLMs, as well as the effectiveness of four editing methods in updating the outdated facts. Our results show that 1) outdatedness is a critical problem across state-of-the-art LLMs; 2) LLMs output inconsistent answers when prompted with slight variations of the question prompt; and 3) the performance of the state-of-the-art knowledge editing algorithms is very limited, as they can not reduce the cases of outdatedness and output inconsistency.

Guoxiong Gao, Haocheng Ju, Jiedong Jiang, Zihan Qin, Bin Dong

The interactive theorem prover Lean enables the verification of formal mathematical proofs and is backed by an expanding community. Central to this ecosystem is its mathematical library, mathlib4, which lays the groundwork for the formalization of an expanding range of mathematical theories. However, searching for theorems in mathlib4 can be challenging. To successfully search in mathlib4, users often need to be familiar with its naming conventions or documentation strings. Therefore, creating a semantic search engine that can be used easily by individuals with varying familiarity with mathlib4 is very important. In this paper, we present a semantic search engine for mathlib4 that accepts informal queries and finds the relevant theorems. We also establish a benchmark for assessing the performance of various search engines for mathlib4.

Mingyang Wang, Lukas Lange, Heike Adel, Jannik Strötgen, Hinrich Schuetze

To ensure large language models contain up-to-date knowledge, they need to be updated regularly. However, model editing is challenging as it might also affect knowledge that is unrelated to the new data. State-of-the-art methods identify parameters associated with specific knowledge and then modify them via direct weight updates. However, these locate-and-edit methods suffer from heavy computational overhead and lack theoretical validation. In contrast, directly fine-tuning the model on requested edits affects the model’s behavior on unrelated knowledge, and significantly damages the model’s generation fluency and consistency. To address these challenges, we propose SAUL, a streamlined model editing method that uses sentence concatenation with augmented random facts for generation regularization. Evaluations on three model editing benchmarks show that is a practical and reliable solution for model editing outperforming state-of-the-art methods while maintaining generation quality and reducing computational overhead.

Alexander Tsvetkov, Alon Kipnis

Large Language Models (LLMs) are increasingly deployed in user-facing applications worldwide, necessitating handling multiple languages across various tasks. We propose a metric called Information Parity (IP) that can predict an LLM’s capabilities across multiple languages in a task-agnostic manner. IP is well-motivated from an information theoretic perspective: it is associated with the LLM’s efficiency of compressing the text in a given language compared to a reference language. We evaluate IP and other popular metrics such as Tokenization Parity (TP) and Tokenizer Fertility (TF) on several variants of open-sourced LLMs (Llama2, Gemma, Mistral). Among all metrics known to us, IP is better correlated with existing task-specific benchmark scores from the literature and thus better predicts such scores in a certain language. These findings show that IP may be useful for ranking multilingual LLMs’ capabilities regardless of the downstream task.

Chen Xu, Wenjie Wang, Yuxin Li, Liang Pang, Jun Xu, Tat-Seng Chua

Recently, Large Language Models (LLMs) have demonstrated a superior ability to serve as ranking models. However, concerns have arisen as LLMs will exhibit discriminatory ranking behaviors based on users’ sensitive attributes (gender). Worse still, in this paper, we identify a subtler form of discrimination in LLMs, termed implicit ranking unfairness, where LLMs exhibit discriminatory ranking patterns based solely on non-sensitive user profiles, such as user names. Such implicit unfairness is more widespread but less noticeable, threatening the ethical foundation. To comprehensively explore such unfairness, our analysis will focus on three research aspects: (1) We propose an evaluation method to investigate the severity of implicit ranking unfairness. (2) We uncover the reasons for causing such unfairness. (3) To mitigate such unfairness effectively, we utilize a pair-wise regression method to conduct fair-aware data augmentation for LLM fine-tuning. The experiment demonstrates that our method outperforms existing approaches in ranking fairness, achieving this with only a small reduction in accuracy. Lastly, we emphasize the need for the community to identify and mitigate the implicit unfairness, aiming to avert the potential deterioration in the reinforced human-LLMs ecosystem deterioration.

Lei Yu, Meng Cao, Jackie CK Cheung, Yue Dong

State-of-the-art language models (LMs) sometimes generate that misalign with world knowledge. To explore the mechanistic causes of these hallucinations, we create diagnostic datasets with subject-relation queries and adapt interpretability methods to trace hallucinations through internal model representations. We discover two general and distinct mechanistic causes of hallucinations shared across LMs (Llama-2, Pythia, GPT-J): 1) : insufficient subject attribute knowledge in lower layer MLPs, and 2) : failure to select the correct object attribute in upper layer attention heads. We also found these two internal mechanistic causes of hallucinations are reflected in external manifestations. Based on insights from our mechanistic analysis, we propose a novel hallucination mitigation method through targeted restoration of the LM’s internal fact recall pipeline, demonstrating superior performance compared to baselines.

Zhaohui Wei, Lizi Liao, Xiaoyu Du, Xinguang Xiang

In the realm of dialogue-to-image retrieval, the primary challenge is to fetch images from a pre-compiled database that accurately reflect the intent embedded within the dialogue history. Existing methods often overemphasize inter-modal alignment, neglecting the nuanced nature of conversational context. Dialogue histories are frequently cluttered with redundant information and often lack direct image descriptions, leading to a substantial disconnect between conversational content and visual representation. This study introduces VCU, a novel framework designed to enhance the comprehension of dialogue history and improve cross-modal matching for image retrieval. VCU leverages large language models (LLMs) to perform a two-step extraction process. It generates precise image-related descriptions from dialogues, while also enhancing visual representation by utilizing object-list texts associated with images. Additionally, auxiliary query collections are constructed to balance the matching process, thereby reducing bias in similarity computations. Experimental results demonstrate that VCU significantly outperforms baseline methods in dialogue-to-image retrieval tasks, highlighting its potential for practical application and effectiveness in bridging the gap between dialogue context and visual content.

Guo Tang, Zheng Chu, Wenxiang Zheng, Ming Liu, Bing Qin

Situational awareness refers to the capacity to perceive and comprehend the present context and anticipate forthcoming events, which plays a critical role in aiding decision-making, anticipating potential issues, and adapting to dynamic circumstances. Nevertheless, the situational awareness capabilities of large language models have not yet been comprehensively assessed. To address this, we propose SA-Bench, a comprehensive benchmark that covers three tiers of situational awareness capabilities, covering environment perception, situation comprehension and future projection. SA-Bench provides a comprehensive evaluation to explore the situational awareness capabilities of LLMs. We conduct extensive experiments on advanced LLMs, including GPT-4, LLaMA3, Qwen1.5, among others. Our experimental results indicate that even SOTA LLMs still exhibit substantial capability gaps compared to humans. In addition, we thoroughly analysis and examine the challenges encountered by LLMs across various tasks, as well as emphasize the deficiencies they confront. We hope SA-Bench will foster research within the field of situational awareness.

Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan

Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the overall preference annotations of responses do not fully capture the fine-grained quality of model outputs in complex multi-step reasoning tasks, such as mathematical reasoning. To address this limitation, we introduce a novel algorithm called Step-level Value Preference Optimization (SVPO). Our approach employs Monte Carlo Tree Search (MCTS) to automatically annotate step-level preferences for multi-step reasoning. Furthermore, from the perspective of learning-to-rank, we train an explicit value model to replicate the behavior of the implicit reward model, complementing standard preference optimization. This value model enables the LLM to generate higher reward responses with minimal cost during inference. Experimental results demonstrate that our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks.

Qian Chen, Dongyang Li, Xiaofeng He, Hongzhao Li, Hongyu Yi

The black-box nature of deep learning models in NLP hinders their widespread application. The research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature interactions. Recent works model non-contiguous combinations with a time-costly greedy search in Eculidean spaces, neglecting underlying linguistic information in feature representations. In this work, we introduce a novel method, namely Poincare Explanation (PE), for modeling feature interactions with hyperbolic spaces in a time efficient manner.Specifically, we take building text hierarchies as finding spanning trees in hyperbolic spaces. First we project the embeddings into hyperbolic spaces to elicit inherit semantic and syntax hierarchical structures. Then we propose a simple yet effective strategy to calculate Shapley score. Finally we build the the hierarchy with proving the constructing process in the projected space could be viewed as building a minimum spanning tree and introduce a time efficient building algorithm. Experimental results demonstrate the effectiveness of our approach. Our code is available at https://anonymous.4open.science/r/PE-747B.

Jiaming Shen, Tianqi Liu, Jialu Liu, Zhen Qin, Jay Pavagadhi, Simon Baumgartner, Michael Bendersky

The popularity of automated news headline generation has surged with advancements in pre-trained language models. However, these models often suffer from the “hallucination” problem, where the generated headline is not fully supported by its source article. Efforts to address this issue have predominantly focused on English, using over-simplistic classification schemes that overlook nuanced hallucination types. In this study, we introduce the first multilingual, fine-grained news headline hallucination detection dataset that contains over 11 thousand <article, headline> pairs in 5 languages, each annotated with detailed hallucination types by experts. We conduct extensive experiments on this dataset under two settings. First, we implement several supervised fine-tuning approaches as preparatory solutions and demonstrate this dataset’s challenges and utilities. Second, we test various large language models’ in-context learning abilities and propose two novel techniques, language-dependent demonstration selection and coarse-to-fine prompting, to boost the few-shot hallucination detection performance in terms of the example-F1 metric. We release this dataset to foster further research in multilingual, fine-grained headline hallucination detection.

Yinhao Bai, Zhixin Han, Yuhua Zhao, Hang Gao, Zhuowei Zhang, Xunzhi Wang, Mengting Hu

Aspect-based sentiment analysis (ABSA) aims to predict aspect-based elements from the given text, mainly including four elements, i.e., aspect category, sentiment polarity, aspect term, and opinion term. Extracting pair, triple, or quad of elements is defined as compound ABSA. Due to its challenges and practical applications, such a compound scenario has become an emerging topic. Recently, large language models (LLMs), e.g. ChatGPT and LLaMA, present impressive abilities in tackling various human instructions. In this work, we are particularly curious whether LLMs still possess superior performance in handling compound ABSA tasks. To assess the performance of LLMs, we design a novel framework, called ChatABSA. Concretely, we design two strategies: constrained prompts, to automatically organize the returned predictions; post-processing, to better evaluate the capability of LLMs in recognition of implicit information. The overall evaluation involves 5 compound ABSA tasks and 8 publicly available datasets. We compare LLMs with few-shot supervised baselines and fully supervised baselines, including corresponding state-of-the-art (SOTA) models on each task. Experimental results show that ChatABSA exhibits excellent aspect-based sentiment analysis capabilities and overwhelmingly beats few-shot supervised methods under the same few-shot settings. Surprisingly, it can even outperform fully supervised methods in some cases. However, in most cases, it underperforms fully supervised methods, and there is still a huge gap between its performance and the SOTA method. Moreover, we also conduct more analyses to gain a deeper understanding of its sentiment analysis capabilities.

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou 等

Improving the performance of large language models (LLMs) in complex question-answering (QA) scenarios has always been a research focal point. Recent studies have attempted to enhance LLMs’ performance by combining step-wise planning with external retrieval. While effective for advanced models like GPT-3.5, smaller LLMs face challenges in decomposing complex questions, necessitating supervised fine-tuning. Previous work has relied on manual annotation and knowledge distillation from teacher LLMs, which are time-consuming and not accurate enough. In this paper, we introduce a novel framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs). LLMs fine-tuned with this data have improved planning capabilities, better equipping them to handle complex QA tasks that involve retrieval. Evaluations on multiple datasets, including our newly proposed benchmark, highlight the effectiveness of our framework and the benefits of KG-derived planning data.

Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng

Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post “in a funny tone” with “no hashtag”). Despite this, most evaluations focus solely on synthetic data. To address this, we introduce RealInstruct, the first benchmark designed to evaluate LLMs’ ability to follow real-world multi-constrained instructions by leveraging queries real users asked AI assistants. We also investigate model-based evaluation as a cost-effective alternative to human annotation for this task. Our findings reveal that even the proprietary GPT-4 model fails to meet at least one constraint on over 21% of instructions, highlighting the limitations of state-of-the-art models. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline, which enhances LLMs’ ability to follow constraints. DeCRIM works by decomposing the original instruction into a list of constraints and using a Critic model to decide when and where the LLM’s response needs refinement. Our results show that DeCRIM improves Mistral’s performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback. Moreover, we demonstrate that with strong feedback, open-source LLMs with DeCRIM can outperform GPT-4 on both benchmarks.