论文检索

Yanzhen Shen, Yu Zhang, Yunyi Zhang, Jiawei Han

Entity set expansion, taxonomy expansion, and seed-guided taxonomy construction are three representative tasks that can be applied to automatically populate an existing taxonomy with emerging concepts. Previous studies view them as three separate tasks. Therefore, their proposed techniques usually work for one specific task only, lacking generalizability and a holistic perspective. In this paper, we aim at a unified solution to the three tasks. To be specific, we identify two common skills needed for entity set expansion, taxonomy expansion, and seed-guided taxonomy construction: finding “siblings” and finding “parents”. We propose a taxonomy-guided instruction tuning framework to teach a large language model to generate siblings and parents for query entities, where the joint pre-training process facilitates the mutual enhancement of the two skills. Extensive experiments on multiple benchmark datasets demonstrate the efficacy of our proposed TaxoInstruct framework, which outperforms task-specific baselines across all three tasks.

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity often fail to reflect enough information, hindering the interpretation of retrieval results. In addition, this process primarily focuses on global semantics, overlooking the finer-grained semantic relationships between the query and the document’s content. In this paper, we introduce a novel method, \textbf{Ge}neration \textbf{A}ugmented \textbf{R}etrieval (\textbf{GeAR}), which not only improves the global document-query similarity through contrastive learning, but also integrates well-designed fusion and decoding modules. This enables GeAR to generate relevant context within the documents based on a given query, facilitating learning to retrieve local fine-grained information.Furthermore, when used as a retriever, GeAR does not incur any additional computational cost over bi-encoders. GeAR exhibits competitive retrieval performance across diverse scenarios and tasks. Moreover, qualitative analysis and the results generated by GeAR provide novel insights into the interpretation of retrieval results. The code, data, and models will be released at https://github.com/microsoft/LMOps.

Yifu Qiu, Varun R. Embar, Yizhe Zhang, Navdeep Jaitly, Shay B. Cohen, Benjamin Han

Recent advancements in long-context language models (LCLMs) promise to transform Retrieval-Augmented Generation (RAG) by simplifying pipelines. With their expanded context windows, LCLMs can process entire knowledge bases and perform retrieval and reasoning directly – a capability we define as In-Context Retrieval and Reasoning (ICR^2). However, existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts. To address this, we introduce ICR^2, a benchmark that evaluates LCLMs in more realistic scenarios by including confounding passages retrieved with strong retrievers. We then propose three methods to enhance LCLM performance: (1) retrieve-then-generate fine-tuning, (2) retrieval-attention-probing, which uses attention heads to filter and de-noise long contexts during decoding, and (3) joint retrieval head training alongside the generation head. Our evaluation of five well-known LCLMs on LOFT and ICR^2 demonstrates significant gains with our best approach applied to Mistral-7B: +17 and +15 points by Exact Match on LOFT, and +13 and +2 points on ICR^2, compared to vanilla RAG and supervised fine-tuning, respectively. It even outperforms GPT-4-Turbo on most tasks despite being a much smaller model.

Bihan Zhou, HaoPeng Ren, Li Yuan, Yi Cai, Liuwen Cao, Zikun Deng

Knowledge editing emerges as a promising approach for updating target knowledge in Large Language Models (LLMs) in a timely manner, thereby preventing undesirable behaviors stemming from outdated, inaccurate, or incomplete knowledge. However, existing methods mainly focus on instance-level editing, which is prone to over-editing risk featuring knowledge degradation and general ability deterioration, due to redundant instance-specific modifications for knowledge. To mitigate the over-editing risk, we explore the rule-level editing problem that avoids case-by-case modification by generalizing rule-level knowledge to update rule-derived instances. We further construct a benchmark called RuleEdit for systematic evaluation on rule-level editing. Moreover, we propose a Rule-Transfer Editing (RTE) method to facilitate effective updates and generalizations of rule-level knowledge in LLMs. Experimental results highlight our significant improvements, with the enhancements of 28.1% in portability and 8.1% in average performance over the best-performing baselines for LLaMA-2-7B on RULE_{mix}.

Yuzheng Cai, Zhenyue Guo, YiWen Pei, WanRui Bian, Weiguo Zheng

Recent advancements in large language models (LLMs) have shown impressive versatility across various tasks. To eliminate their hallucinations, retrieval-augmented generation (RAG) has emerged as a powerful approach, leveraging external knowledge sources like knowledge graphs (KGs). In this paper, we study the task of KG-driven RAG and propose a novel Similar Graph Enhanced Retrieval-Augmented Generation (SimGRAG) method. It effectively addresses the challenge of aligning query texts and KG structures through a two-stage process: (1) query-to-pattern, which uses an LLM to transform queries into a desired graph pattern, and (2) pattern-to-subgraph, which quantifies the alignment between the pattern and candidate subgraphs using a graph semantic distance (GSD) metric. We also develop an optimized retrieval algorithm that efficiently identifies the top-k subgraphs within 1-second on a 10-million-scale KG. Extensive experiments show that SimGRAG outperforms state-of-the-art KG-driven RAG methods in both question answering and fact verification. Our code is available at https://github.com/YZ-Cai/SimGRAG.

Guiyang Hou, Wenqi Zhang, Zhe Zheng, Yongliang Shen, Weiming Lu

Humans continually engage in reasoning about others’ mental states, a capability known as Theory of Mind (ToM), is essential for social interactions. While this social reasoning capability emerges naturally in human cognitive development, how has the social reasoning capability of Large Language Models (LLMs) evolved during their development process? Various datasets have been proposed to assess LLMs’ social reasoning capabilities, but each is designed with a distinct focus, and none have explored how models’ social reasoning capabilities evolve during model size scaling or reasoning tokens scaling. In light of this, we optimize the evaluation of LLMs’ social reasoning from both data and model perspectives, constructing progressively difficult levels of social reasoning data and systematically exploring how LLMs’ social reasoning capabilities evolve. Furthermore, through an in-depth analysis of DeepSeek-R1’s reasoning trajectories, we identify notable cognitive “Aha Moment” and the reasons for its reasoning errors. Experiments reveal that long-thought logical capabilities and cognitive thinking are key to scaling LLMs’ social reasoning capabilities. By equipping the Qwen2.5-32B-Instruct model with long-thought logical capabilities and cognitive thinking, we achieve an improvement of 19.0 points, attaining social reasoning performance comparable to o1-preview model.

James Xu Zhao, Jimmy Z.J. Liu, Bryan Hooi, See-Kiong Ng

Large language models (LLMs) are widely used for long-form text generation. However, factual errors in the responses would undermine their reliability. Despite growing attention to LLM factuality, the effect of response length on factuality remains underexplored. In this work, we systematically investigate this relationship by first introducing an automatic and bi-level long-form factuality evaluation framework, which achieves high agreement with human annotations while being cost-effective. Using this framework, we conduct controlled experiments and find that longer responses exhibit lower factual precision, confirming the presence of length bias. To explain this phenomenon, we empirically examine three hypotheses: error propagation, long context, and facts exhaustion. Our results reveal that facts exhaustion, where the model gradually exhausts more reliable knowledge, is the primary cause of factual degradation, rather than the other two hypotheses.

Soo Kyung Kim, Hyunsoo Cho

Large Language Models (LLMs) often succumb to adversarial prompts, a phenomenon popularly known as “jailbreaking.” While jailbreaking primarily targets short-term noncompliance with predefined policies, we argue that a deeper vulnerability lies in altering an LLM’s fundamental axiomatic beliefs, such as mathematical or philosophical truths. In this work, we introduce GoodLiar, a reinforcement learning (RL)-based framework that generates deceptive contexts to systematically rewrite an LLM’s core logical or philosophical understandings. By incentivizing an RL agent to produce persuasive and coherent arguments, GoodLiar aims to induce persistent belief shifts, rather than merely influencing immediate judgments of factual truthfulness. %rather than one-off policy breaches. Our approach introduces DA-ILQL, a novel offline RL method that extends ILQL by integrating on-policy data and language exploration to enhance the language discovery and optimization. Through extensive evaluations on multiple LLMs, we show that deceptive contexts discovered by GoodLiar consistently outperform simple multi-turn prompting methods.

Haozhe Wang, Long Li, Chao Qu, Weidi Xu, Fengming Zhu, Wei Chu, Fangzhen Lin

Recent advances in mathematical problem-solving with language models (LMs) integrate chain-of-thought (CoT) reasoning and code execution to harness their complementary strengths. However, existing hybrid frameworks exhibit a critical limitation: they depend on externally dictated instructions or rigid code-integration templates, lacking metacognitive awareness—the capacity to dynamically evaluate intrinsic capabilities and autonomously determine when and how to integrate tools. This rigidity motivates our study of autonomous code integration, enabling models to adapt tool-usage strategies as their reasoning abilities evolve during training.While reinforcement learning (RL) shows promise for boosting LLM reasoning at scale (e.g., DeepSeek-R1), we demonstrate its inefficiency in learning autonomous code integration due to inadequate exploration of the vast combinatorial space of CoT-code interleaving patterns. To address this challenge, we propose a novel Expectation-Maximization (EM) framework that synergizes structured exploration (E-step) with off-policy RL optimization (M-step), creating a self-reinforcing cycle between metacognitive tool-use decisions and evolving capabilities. Experiments reveal our method achieves superior results through improved exploration. Notably, our 7B model improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT.

Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while neglecting oversafety, where the model refuses to answer safe queries. In this paper, we introduce the concept of safety calibration, which systematically addresses both undersafety and oversafety. Specifically, we present VSCBench, a novel dataset of 3,600 image-text pairs that are visually or textually similar but differ in terms of safety, which is designed to evaluate safety calibration across image-centric and text-centric scenarios. Based on our benchmark, we evaluate safety calibration across eleven widely used VLMs. Our extensive experiments revealed major issues with both undersafety and oversafety. We further investigated four approaches to improve the model’s safety calibration. We found that even though some methods effectively calibrated the models’ safety problems, these methods also lead to the degradation of models’ utility. This trade-off underscores the urgent need for advanced calibration methods, and our benchmark provides a valuable tool for evaluating future approaches.

Siqi Ouyang, Xi Xu, Lei Li

Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the historical speech context and past translations so that quality and latency, including computation overhead, can be balanced. Most prior works assume pre-segmented speech, limiting their real-world applicability. In this paper, we propose InfiniSST, a novel approach that formulates SST as a multi-turn dialogue task, enabling seamless translation of unbounded speech. We construct translation trajectories and robust segments from MuST-C with multi-latency augmentation during training and develop a key-value (KV) cache management strategy to facilitate efficient inference. Experiments on MuST-C En-Es, En-De, and En-Zh demonstrate that InfiniSST reduces computation-aware latency by 0.5 to 1 second while maintaining the same translation quality compared to baselines. Ablation studies further validate the contributions of our data construction and cache management strategy. Code is released at https://github.com/LeiLiLab/InfiniSST.

Andrea Pedrotti, Michele Papucci, Cristiano Ciaccio, Alessio Miaschi, Giovanni Puccetti, Felice Dell’Orletta, Andrea Esuli

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation. Moreover, detecting Machine-Generated Text (MGT) remains challenging due to the lack of robust benchmarks that assess generalization to real-world scenarios. In this work, we evaluate the resilience of state-of-the-art MGT detectors (e.g., Mage, Radar, LLM-DetectAIve) to linguistically informed adversarial attacks. We develop a pipeline that fine-tunes language models using Direct Preference Optimization (DPO) to shift the MGT style toward human-written text (HWT), obtaining generations more challenging to detect by current models. Additionally, we analyze the linguistic shifts induced by the alignment and how detectors rely on “linguistic shortcuts” to detect texts. Our results show that detectors can be easily fooled with relatively few examples, resulting in a significant drop in detecting performances. This highlights the importance of improving detection methods and making them robust to unseen in-domain texts. We release code, models, and data to support future research on more robust MGT detection benchmarks.

Anirudh Maiya, Razan Alghamdi, Maria Leonor Pacheco, Ashutosh Trivedi, Fabio Somenzi

The success of Large Language Models (LLMs) in human-AI collaborative decision-making hinges on their ability to provide trustworthy, gradual, and tailored explanations. Solving complex puzzles, such as Sudoku, offers a canonical example of this collaboration, where clear and customized explanations often hold greater importance than the final solution. In this study, we evaluate the performance of five LLMs in solving and explaining 6x6 Sudoku puzzles. While one LLM demonstrates limited success in solving puzzles, none can explain the solution process in a manner that reflects strategic reasoning or intuitive problem-solving. These findings underscore significant challenges that must be addressed before LLMs can become effective partners in human-AI collaborative decision-making.

Siqi Fan, Xuezhi Fang, Xingrun Xing, Peng Han, Shuo Shang, Yequan Wang

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, recent dynamic computation methods show that not all components are required for inference, enabling a training-free pipeline.In this paper, we focus on the dynamic depth of LLM generation. A token-position aware layer skipping framework is proposed to save 1.5x times operations efficiently while maintaining performance.We first observed that tokens predicted later have lower perplexity and thus require less computation. Then, we propose a training-free algorithm called Position-Aware Depth Decay Decoding (), which leverages a power-law decay function, \left\lfloor L \times (\alpha^i) \right\rfloor, to determine the number of layers to retain when generating token T_i. Remarkably, without any retraining, the achieves success across a wide range of generation tasks for the first time.Experiments on large language models (the Llama) with 7 \sim 70 billion parameters show that can achieve an average 1.5x speedup compared with the full-inference pipeline while maintaining comparable performance with nearly no performance drop (<1\%) on the GSM8K and BBH benchmarks.

Jiaqi Li, Yixuan Tang, Yi Yang

Large language models (LLMs) demonstrate remarkable capabilities but face challenges from hallucinations, which typically arise from insufficient knowledge or context. While instructing LLMs to acknowledge knowledge limitations by responding with “I don’t know” appears promising, we find that models consistently struggle with admitting knowledge gaps. This challenge may originate from current instruction datasets that emphasise answer generation over knowledge boundary awareness. To address this limitation, we introduce **U**ncertainty-and-**S**ensitivity-Aware Tuning **(US-Tuning)**, a novel two-stage approach for contextual question answering (QA). The first stage enhances LLMs’ ability to recognise their knowledge boundaries, while the second stage reinforces instruction adherence through carefully designed causal prompts. Our experimental results demonstrate that US-Tuning not only significantly reduces incorrect answers in contextual QA but also improves models’ faithfulness to their parametric knowledge, mitigating hallucinations in general QA tasks. Our fine-tuned Llama2-7B model achieves up to a 34.7% improvement in handling out-of-knowledge questions and outperforms GPT-4 by 4.2% in overall performance.

Hanlun Zhu, Yunshi Lan, Xiang Li, Weining Qian

As the insight of knowledge storage in language models deepens, the ability to perform CRUD (Create, Read, Update, Delete) operations on language models becomes increasingly indispensable for satisfying the demands of managing rapidly updating knowledge. Considering the high cost of fine-tuning language models, model editing methods with low cost are usually required to manipulate models’ knowledge. The evidence suggests that modules carrying knowledge in a Transformer module are primarily the MLP blocks, thus we propose iReVa, a method that explicitly initializes and retrofits key-value pairs into MLP blocks to construct a new mapping of a piece of knowledge without damaging the irrelevant knowledge. In comparison to existing methods, iReVa reveals better interpretability and a stronger capacity for carrying traceable edits. Experiment results on a series of GPT series models show our prominent performance on edit success and generalization without influencing specificity. We also made the first attempt to conduct a knowledge withdrawal test of iReVa. Our codes are available at https://github.com/timberflow/iReVa.

Qiji Zhou, YiFan Gong, Guangsheng Bao, Hongjie Qiu, Jinqiang Li, Xiangrong Zhu, Huajian Zhang, Yue Zhang

Counterfactual reasoning is crucial for robust video understanding but remains underexplored in existing multimodal benchmarks. In this paper, we introduce **COVER** (**CO**unterfactual **V**id**E**o **R**easoning), a multidimensional multimodal benchmark that systematically evaluates MLLMs across the abstract-concrete and perception-cognition dimensions. Beyond prior multimodal benchmarks, COVER decomposes complex queries into structured sub-questions, enabling fine-grained reasoning analysis. Experiments on commercial and open-source models reveal a strong correlation between sub-question accuracy and counterfactual reasoning performance, highlighting the role of structured inference in video understanding. Furthermore, our results suggest a key insight: enhancing the reasoning capability of models is essential for improving the robustness of video understanding. COVER establishes a new standard for assessing MLLMs’ logical reasoning abilities in dynamic environments. Our work is available at https://github.com/gongyifan-hash/COVER-Benchmark.

Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Kun Wang, Qingsong Wen, Yang Wang

Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications. However, safeguarding these systems from malicious queries receives relatively little attention, while methods for single-agent safety are challenging to transfer. In this paper, we explore MAS safety from a topological perspective, aiming at identifying structural properties that enhance security. To this end, we propose NetSafe framework, unifying diverse MAS workflows via iterative RelCom interactions to enable generalized analysis. We identify several critical phenomena for MAS under attacks (misinformation, bias, and harmful content), termed as \textit{Agent Hallucination}, \textit{Aggregation Safety} and \textit{Security Bottleneck}. Furthermore, we verify that highly connected and larger systems are more vulnerable to adversarial spread, with task performance in a Star Graph Topology decreasing by 29.7%. In conclusion, our work introduces a new perspective on MAS safety and discovers unreported phenomena, offering insights and posing challenges to the community.

Felix Drinkall, Stefan Zohren, Michael McMahon, Janet B. Pierrehumbert

Macroeconomic fluctuations and the narratives that shape them form a mutually reinforcing cycle: public discourse can spur behavioural changes leading to economic shifts, which then result in changes in the stories that propagate. We show that shifts in semantic embedding space can be causally linked to real-world market shocks or deviations from the expected market behaviour (sec:market_shocks). Furthermore, we show how partisanship can influence the predictive power of text for market fluctuations and shape reactions to those same shocks. We also provide some evidence that text-based signals are particularly salient during rare events such as COVID-19, highlighting the value of language data as an exogenous variable in economic forecasting. Our findings underscore the bidirectional relationship between news outlets and market shocks, offering a novel empirical approach to studying their effect on each other.

Wei Yao, Wenkai Yang, Ziqiao Wang, Yankai Lin, Yong Liu

As large language models advance toward superhuman performance, ensuring their alignment with human values and abilities grows increasingly complex. Weak-to-strong generalization offers a promising approach by leveraging predictions from weaker models to guide stronger systems, but its effectiveness could be constrained by the inherent noise and inaccuracies in these weak predictions. To address this, we propose a theoretically grounded approach that replaces forward KL divergence—whose mass-covering behavior risks overfitting to imperfect weak signals—with reverse KL divergence. Reverse KL divergence’s zero-forcing effect prioritizes high-confidence predictions, effectively mitigating the influence of unreliable weak supervision. Theoretically, we extend existing bounds and derive tighter lower bounds for both forward and reverse KL divergence. Notably, when a sufficiently pre-trained strong model is fine-tuned on the last linear layer, reverse KL guarantees that it outperforms its weak supervisor by the magnitude of their disagreement. Empirically, we demonstrate that reverse KL and reverse cross-entropy not only enable strong models to outperform those trained with forward KL and standard cross-entropy across most settings, but also exhibit greater robustness to noisy labels.