论文检索

Yuetong Rong, Yijun Mo

Implicit Discourse Relation Recognition (IDRR) is an important task to classify the discourse relation sense between argument pairs without an explicit connective. Recently, prompt learning methods have demonstrated success in IDRR. However, prior work primarily transform IDRR into a connective-cloze task based on the masked language model (MLM), which limits the predicted connective to one single token. Also, they fail to fully exploit critical semantic features shared among various forms of templates. In this paper, we propose NCPrompt, an NSP-based prompt learning and Contrastive learning method for IDRR. Specifically, we transform the IDRR task into a next sentence prediction (NSP) task, which can allow various-length answer connectives and enlarge the construction of the verbalizer for prompt-learning methods. Also, we notice that various prompt templates naturally constitute positive samples applied for self-supervised contrastive learning. And the usage of NSP naturally creates hard negative samples by introducing different candidate connectives between the same example. To our knowledge, we are the first to combine self-supervised contrastive learning with prompt learning to obtain high-quality semantic representations. Experiments on the PDTB 3.0 corpus have demonstrated the effectiveness and superiority of our model.

Kaisi Guan, Qian Cao, Yuchong Sun, Xiting Wang, Ruihua Song

Retrieval Augmented Generation (RAG) system is important in domains such as e-commerce, which has many long-tail entities and frequently updated information. Most existing works adopt separate modules for retrieval and generation, which may be suboptimal since the retrieval task and the generation task cannot benefit from each other to improve performance. We propose a novel Backbone Shared RAG framework (BSharedRAG). It first uses a domain-specific corpus to continually pre-train a base model as a domain-specific backbone model and then trains two plug-and-play Low-Rank Adaptation (LoRA) modules based on the shared backbone to minimize retrieval and generation losses respectively. Experimental results indicate that our proposed BSharedRAG outperforms baseline models by 5% and 13% in Hit@3 upon two datasets in retrieval evaluation and by 23% in terms of BLEU-3 in generation evaluation. Our codes, models, and dataset are available at https://bsharedrag.github.io.

Xiao Wei, Haoran Chen, Hang Yu, Hao Fei, Qian Liu

Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from their extensive world knowledge acquired through extensive pretraining. While approaches like Chain-of-Thought (CoT) have shown promise in enhancing LLMs’ reasoning capabilities, mitigating the influence of inaccurate commonsense knowledge remains a challenge, particularly for small-scale LLMs (e.g., those with less than 10B parameters). In this work, we propose a novel method named Guided Knowledge Generation (GuideKG) to address these issues. It presents three advantages: (i) Employing LLMs to generate knowledge explanations and to automatically assign labels based on the probability of correct answers eliminates the need for costly manual annotation in subsequent training. (ii) Training a new module called the ‘Know-Filter’, which is used to evaluate knowledge, and we have introduced a new loss to enhance its performance. (iii) Evaluating the effectiveness of knowledge fragments at the sentence level and fusing them allows for precise control over the generation process of LLMs. We evaluate our GuideKG on small-scale LLMs and show that it outperforms all baselines on four widely-used commonsense reasoning benchmarks. Moreover, our experiments reveal that, with proper guidance, small-scale LLMs can exhibit exceptional performance in commonsense reasoning.

Silin Meng, Yiwei Wang, Cheng-Fu Yang, Nanyun Peng, Kai-Wei Chang

Path planning is a fundamental scientific problem in robotics and autonomous navigation, requiring the derivation of efficient routes from starting to destination points while avoiding obstacles. Traditional algorithms like A* and its variants are capable of ensuring path validity but suffer from significant computational and memory inefficiencies as the state space grows. Conversely, large language models (LLMs) excel in broader environmental analysis through contextual understanding, providing global insights into environments. However, they fall short in detailed spatial and temporal reasoning, often leading to invalid or inefficient routes. In this work, we propose LLM-A*, an new LLM based route planning method that synergistically combines the precise pathfinding capabilities of A* with the global reasoning capability of LLMs. This hybrid approach aims to enhance pathfinding efficiency in terms of time and space complexity while maintaining the integrity of path validity, especially in large-scale scenarios. By integrating the strengths of both methodologies, LLM-A* addresses the computational and memory limitations of conventional algorithms without compromising on the validity required for effective pathfinding.

Zeliang Zhang, Zhuo Liu, Mingqian Feng, Chenliang Xu

CLIP has demonstrated great versatility in adapting to various downstream tasks, such as image editing and generation, visual question answering, and video understanding. However, CLIP-based applications often suffer from misunderstandings regarding user intent, leading to discrepancies between the required number of objects and the actual outputs in image generation tasks. In this work, we empirically investigate the quantity bias in CLIP. By carefully designing different experimental settings and datasets, we comprehensively evaluate CLIP’s understanding of quantity from text, image, and cross-modal perspectives. Our experimental results reveal a quantity bias in CLIP embeddings, impacting the reliability of downstream tasks.

Xiaoyi Bao, Jinghang Gu, Zhongqing Wang, Minjie Qiang, Chu-Ren Huang

As a complex task that requires rich information input, features from various aspects have been utilized in event extraction. However, most of the previous works ignored the value of glyph, which could contain enriched semantic information and can not be fully expressed by the pre-trained embedding in hieroglyphic languages like Chinese. We argue that, compared with combining the sophisticated textual features, glyphic information from visual modality could provide us with extra and straight semantic information in extracting events. Motivated by this, we propose a glyphic multi-modal Chinese event extraction model with hieroglyphic images to capture the intra- and inter-character morphological structure from the sequence. Extensive experiments build a new state-of-the-art performance in the ACE2005 Chinese and KBP Eval 2017 dataset, which underscores the effectiveness of our proposed glyphic event extraction model, and more importantly, the glyphic feature can be obtained at nearly zero cost.

Junsoo Park, Seungyeon Jwa, Ren Meiying, Daeyoung Kim, Sanghyuk Choi

Employing Large Language Models (LLMs) to assess the quality of generated responses has become a widely adopted evaluation method. Specifically, instruct-tuned models and fine-tuned judge models based on open-source LLMs have been reported. While it is known that judge models are vulnerable to certain biases, such as favoring longer answers regardless of content, the specifics of these biases remain under-explored. In this work, we qualitatively identify six types of biases inherent in various judge models. We propose EvalBiasBench as a meta-evaluation collection of hand-crafted test cases for each bias type. Additionally, we present de-biasing dataset construction methods and the associated preference dataset OffsetBias. Experimental results demonstrate that fine-tuning on our dataset significantly enhances the robustness of judge models against biases and improves performance across most evaluation scenarios. We release our datasets and the fine-tuned judge model to public.

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing methods heavily rely on high-quality positive-negative training pairs, suffering from noisy positive responses that are barely distinguishable from negative ones. Given recent LLMs’ proficiency in generating helpful responses, this work pivots towards a new research question: **can we achieve alignment using solely human-annotated negative samples, preserving helpfulness while reducing harmfulness?** For this purpose, we propose Distributional Dispreference Optimization (D^2O), which maximizes the discrepancy between dispreferred responses and the generated non-negative ones. In this way, D^2O effectively eschews harmful information without incorporating noisy positive samples, while avoiding collapse using self-generated responses as anchors. We demonstrate that D^2O can be regarded as learning a distributional preference model reflecting human dispreference against negative responses, which is theoretically an upper bound of the instance-level DPO. Extensive experiments manifest that our method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Shuoming Zhang, Jiacheng Zhao, Chunwei Xia, Zheng Wang, Yunji Chen, Huimin Cui

Compilers are complex software containing millions of lines of code, taking years to develop. This paper investigates to what extent Large Language Models (LLMs) can replace hand-crafted compilers in translating high-level programming languages to machine instructions, using C to x86 assembly as a case study. We identify two challenges of using LLMs for code translation and introduce two novel data pre-processing techniques to address the challenges: numerical value conversion and training data resampling. While only using a 13B model, our approach achieves a behavioral accuracy of over 91%, outperforming the much larger GPT-4 Turbo model by over 50%. Our results are encouraging, showing that LLMs have the potential to transform how compilation tools are constructed.

Jiayuan Su, Jing Luo, Hongwei Wang, Lu Cheng

This study aims to address the pervasive challenge of quantifying uncertainty in large language models (LLMs) with black-box API access. Conformal Prediction (CP), known for its model-agnostic and distribution-free features, is a desired approach for various LLMs and data distributions. However, existing CP methods for LLMs typically assume access to the logits, which are unavailable for some API-only LLMs. In addition, logits are known to be miscalibrated, potentially leading to degraded CP performance. To tackle these challenges, we introduce a novel CP method that (1) is tailored for API-only LLMs without logit-access; (2) minimizes the size of prediction sets; and (3) ensures a statistical guarantee of the user-defined coverage. The core idea of this approach is to formulate nonconformity measures using both coarse-grained (i.e., sample frequency) and fine-grained uncertainty notions (e.g., semantic similarity). Experimental results on both close-ended and open-ended Question Answering tasks show our approach can mostly outperform the logit-based CP baselines.

Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth, Yang Li

In this work, we introduce a novel approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks. Our approach prompts LLM agents to decompose a given task into manageable subtasks (i.e., to make a plan), and to continuously introspect upon the suitability and results of their actions. We implement a three-fold introspective intervention: 1) anticipatory reflection on potential failures and alternative remedy before action execution, 2) post-action alignment with subtask objectives and backtracking with remedy to ensure utmost effort in plan execution, and 3) comprehensive review upon plan completion for future strategy refinement. By deploying and experimenting with this methodology—a zero-shot approach—within WebArena for practical tasks in web environments, our agent demonstrates superior performance with a success rate of 23.5% over existing zero-shot methods by 3.5%. The experimental results suggest that our introspection-driven approach not only enhances the agent’s ability to navigate unanticipated challenges through a robust mechanism of plan execution, but also improves efficiency by reducing the number of trials and plan revisions by 45% needed to achieve a task.

Joseph Marvin Imperial, Harish Tayyar Madabushi

Specialized lexicons are collections of words with associated constraints such as special definitions, specific roles, and intended target audiences. These constraints are necessary for content generation and documentation tasks (e.g., writing technical manuals or children’s reading materials), where the goal is to reduce the ambiguity of text content and increase its overall readability for a specific group of audience. Understanding how large language models can capture these constraints can help researchers build better, more impactful tools for wider use beyond the NLP community. Towards this end, we introduce SpeciaLex, a benchmark for evaluating a language model’s ability to follow specialized lexicon-based constraints across 18 diverse subtasks with 1,785 test instances covering core tasks of Checking, Identification, Rewriting, and Open Generation. We present an empirical evaluation of 15 open and closed-source LLMs and discuss insights on how factors such as model scale, openness, setup, and recency affect performance upon evaluating with the benchmark.

Wen-Shuo Chao, Zhi Zheng, Hengshu Zhu, Hao Liu

Large Language Models (LLMs) demonstrate robust capabilities across various fields, leading to a paradigm shift in LLM-enhanced Recommender System (RS). Research to date focuses on point-wise and pair-wise recommendation paradigms, which are inefficient for LLM-based recommenders due to high computational costs. However, existing list-wise approaches also fall short in ranking tasks due to misalignment between ranking objectives and next-token prediction. Moreover, these LLM-based methods struggle to effectively address the order relation among candidates, particularly given the scale of ratings. To address these challenges, this paper introduces the large language model framework with Aligned Listwise Ranking Objectives (ALRO). ALRO is designed to bridge the gap between the capabilities of LLMs and the nuanced requirements of ranking tasks. Specifically, ALRO employs explicit feedback in a listwise manner by introducing soft lambda loss, a customized adaptation of lambda loss designed for optimizing order relations. This mechanism provides more accurate optimization goals, enhancing the ranking process. Additionally, ALRO incorporates a permutation-sensitive learning mechanism that addresses position bias, a prevalent issue in generative models, without imposing additional computational burdens during inference. Our evaluative studies reveal that ALRO outperforms both existing embedding-based recommendation methods and LLM-based recommendation baselines.

Ruiyang Ren, Peng Qiu, Yingqi Qu, Jing Liu, Wayne Xin Zhao, Hua Wu, Ji-Rong Wen, Haifeng Wang

Due to the excellent capacities of large language models (LLMs), it becomes feasible to develop LLM-based agents for reliable user simulation. Considering the scarcity and limit (e.g., privacy issues) of real user data, in this paper, we conduct large-scale user simulations for the web search scenario to improve the analysis and modeling of user search behavior. Specially, we propose BASES, a novel user simulation framework with LLM-based agents, designed to facilitate comprehensive simulations of web search user behaviors. Our simulation framework can generate unique user profiles at scale, which subsequently leads to diverse search behaviors. To demonstrate the effectiveness of BASES, we conduct evaluation experiments based on two human benchmarks in both Chinese and English, demonstrating that BASES can effectively simulate large-scale human-like search behaviors. To further accommodate the research on web search, we develop WARRIORS, a new large-scale dataset encompassing web search user behaviors, including both Chinese and English versions, which can greatly bolster research in the field of information retrieval.

Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA to enhance document retrieval by reformulating queries. Many works have attempted to improve query rewriting in smaller models to avoid rewriting with costly LLMs, and the most common method is to employ reinforcement learning for feedback training. However, current methods require annotations (labeled relevant documents or downstream answers) or predesigned rewards for feedback, lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose RaFe, a framework for training query rewriting models. By leveraging reranker, RaFe provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models. Experimental results demonstrate that with a general and publicly available reranker, RaFe can effectively steer the training for rewrite models.

Xiang Liu, Peijie Dong, Xuming Hu, Xiaowen Chu

Current long-context benchmarks primarily focus on retrieval-based tests, requiring Large Language Models (LLMs) to locate specific information within extensive input contexts, such as the needle-in-a-haystack (NIAH) benchmark. Long-context generation refers to the ability of a language model to generate coherent and contextually accurate text that spans across lengthy passages or documents. While recent studies show strong performance on NIAH and other retrieval-based long-context benchmarks, there is a significant lack of benchmarks for evaluating long-context generation capabilities. To bridge this gap and offer a comprehensive assessment, we introduce a synthetic benchmark, LongGenBench, which allows for flexible configurations of customized generation context lengths. LongGenBench advances beyond traditional benchmarks by redesigning the format of questions and necessitating that LLMs respond with a single, cohesive long-context answer. Upon extensive evaluation using LongGenBench, we observe that: (1) both API accessed and open source models exhibit performance degradation in long-context generation scenarios, ranging from 1.2% to 47.1%; (2) different series of LLMs exhibit varying trends of performance degradation, with the Gemini-1.5-Flash model showing the least degradation among API accessed models, and the Qwen2 series exhibiting the least degradation in LongGenBench among open source models.

Wanting Ning, Lishuang Li, Xueyang Qin, Yubo Feng, Jingyao Tang

Understanding and analyzing event temporal relations is a crucial task in Natural Language Processing (NLP). This task, known as Event Temporal Relation Extraction (ETRE), aims to identify and extract temporal connections between events in text. Recent studies focus on locating the relative position of event pairs on the timeline by designing logical expressions or auxiliary tasks to predict their temporal occurrence. Despite these advances, this modeling approach neglects the multidimensional information in temporal relation and the hierarchical process of reasoning. In this study, we propose a novel hierarchical modeling approach for this task by introducing a Temporal Cognitive Tree (TCT) that mimics human logical reasoning. Additionally, we also design a integrated model incorporating prompt optimization and deductive reasoning to exploit multidimensional supervised information. Extensive experiments on TB-Dense and MATRES datasets demonstrate that our approach outperforms existing methods.

Shengnan An, Zexiong Ma, Siqi Cai, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen

Towards enhancing the chain-of-thought (CoT) reasoning of large language models (LLMs), much existing work has revealed the effectiveness of straightforward learning on annotated/generated CoT paths. However, there is less evidence yet that reasoning capabilities can be enhanced through a reverse learning process, i.e., learning from potential mistakes in reasoning. To investigate whether LLMs can learn from mistakes, we construct mistake-correction datasets, using GPT-4 to identify and correct the mistakes in inaccurate CoTs. With these mistake-correction datasets, we fine-tune open-source LLMs and arrive at the following conclusions. (1) LLMs can indeed learn from mistakes to enhance their CoT reasoning performances. (2) Compared to CoT data, the mistake-correction data provides additional knowledge on the explanations and reasons for the potential mistakes in CoTs, which consistently contributes to the effectiveness of learning from mistakes. (3) Evolution techniques, especially the correction-centric evolution we introduced, can further enhance the effectiveness of learning from mistakes.

Chuanhong Zhan, Wei Xiang, Liang Chao, Bang Wang

Existing script event prediction task forcasts the subsequent event based on an event script chain. However, the evolution of historical events are more complicated in real world scenarios and the limited information provided by the event script chain also make it difficult to accurately predict subsequent events. This paper introduces a Causality Graph Event Prediction(CGEP) task that forecasting consequential event based on an Event Causality Graph (ECG). We propose a Semantic Enhanced Distance-sensitive Graph Prompt Learning (SeDGPL) Model for the CGEP task. In SeDGPL, (1) we design a Distance-sensitive Graph Linearization (DsGL) module to reformulate the ECG into a graph prompt template as the input of a PLM; (2) propose an Event-Enriched Causality Encoding (EeCE) module to integrate both event contextual semantic and graph schema information; (3) propose a Semantic Contrast Event Prediction (ScEP) module to enhance the event representation among numerous candidate events and predict consequential event following prompt learning paradigm. Experiment results validate our argument our proposed SeDGPL model outperforms the advanced competitors for the CGEP task.

Donghoon Kim, Gusang Lee, Kyuhong Shim, Byonghyo Shim

Recently, we have observed that Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across various multi-modal applications. To adapt LMMs for downstream tasks, parameter-efficient fine-tuning (PEFT) which only trains additional prefix tokens or modules, has gained popularity. Nevertheless, there has been little analysis of how PEFT works in LMMs. In this paper, we delve into the strengths and weaknesses of each tuning strategy, shifting the focus from the efficiency typically associated with these approaches. We first discover that model parameter tuning methods such as LoRA and Adapters, distort the feature representation space learned during pre-training, limiting the full utilization of pre-trained knowledge. We also demonstrate that prefix-tuning excels at preserving the representation space, despite of its lower performance on downstream tasks. These findings suggest a simple two-step PEFT strategy called Prefix-Tuned PEFT (PT-PEFT), which successively performs prefix-tuning and then other PEFT (i.e., Adapter, LoRA), combines the benefits of both. Experimental results show that PT-PEFT not only improves performance in image captioning and visual question answering compared to vanilla PEFT methods but also helps preserve the representation space of the four pre-trained models.