论文检索

Rong Ma, Lei Wang, Yating Yang, Bo Ma, Rui Dong, Fengyi Yang, Ahtamjan Ahmat, Kaiwen Lu, Xinyue Wang

Event forecasting requires modeling historical event data to predict future events, and achieving accurate predictions depends on effectively capturing the relevant historical information that aids forecasting. Most existing methods focus on entities and structural dependencies to capture historical clues but often overlook implicitly relevant information. This limitation arises from overlooking event semantics and deeper factual associations that are not explicitly connected in the graph structure but are nonetheless critical for accurate forecasting. To address this, we propose a dual-criteria constraint strategy that leverages event semantics for relevance modeling and incorporates a self-supervised semantic filter based on factual event associations to capture implicitly relevant historical information. Building on this strategy, our method, termed ITHI (Integrating Three types of Historical Information), combines sequential event information, periodically repeated event information, and relevant historical information to achieve context-aware event forecasting. We evaluated the proposed ITHI method on three public benchmark datasets, achieving state-of-the-art performance and significantly outperforming existing approaches. Additionally, we validated its effectiveness on two structured temporal knowledge graph forecasting dataset.

Songze Li, Zhiqiang Liu, Zhengke Gui, Huajun Chen, Wen Zhang

Large Language Models (LLMs) exhibit strong reasoning capabilities in complex tasks. However, they still struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA). We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures. Existing methods usually employ resource-intensive, non-scalable workflows reasoning on vanilla KGs, but overlook this gap. To address this challenge, we propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs’ prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries. EoG enables efficient evidence extraction from KGs for precise and robust reasoning, while ensuring low computational costs, scalability, and adaptability across different methods. Furthermore, we propose three graph quality evaluation metrics to analyze query-graph alignment in KGQA task, supported by theoretical validation of our optimization objectives. Extensive experiments on two KGQA benchmark datasets indicate that EoG can effectively generate high-quality KGs and achieve the state-of-the-art performance.

Anant Khandelwal, Manish Gupta, Puneet Agrawal

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and can degrade performance in low conflict settings. We introduce CoCoA (Confidence- and Context-Aware Adaptive Decoding), a novel token-level algorithm for principled conflict resolution and enhanced faithfulness. CoCoA resolves conflict by utilizing confidence-aware measures (entropy gap and contextual peakedness) and the generalized divergence between the parametric and contextual distributions. Crucially, CoCoA maintains strong performance even in low conflict settings. Extensive experiments across multiple LLMs on diverse Question Answering (QA), Summarization, and Long-Form Question Answering (LFQA) benchmarks demonstrate CoCoA’s state-of-the-art performance over strong baselines like AdaCAD. It yields significant gains in QA accuracy, up to 9.2 points on average compared to the strong baseline AdaCAD, and improves factuality in summarization and LFQA by up to 2.5 points on average across key benchmarks. Additionally, it demonstrates superior sensitivity to conflict variations. CoCoA enables more informed, context-aware, and ultimately more faithful token generation.

Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

Large Language Models often contain factually incorrect or outdated knowledge, giving rise to model editing methods for precise knowledge updates. However, current mainstream locate-then-edit approaches exhibit a progressive performance decline during sequential editing, due to inadequate mechanisms for long-term knowledge preservation. To tackle this, we model the sequential editing as a constrained stochastic programming. Given the challenges posed by the cumulative preservation error constraint and the gradually revealed editing tasks, **LyapLock** is proposed. It integrates queuing theory and Lyapunov optimization to decompose the long-term constrained programming into tractable stepwise subproblems for efficient solving. This is the first model editing framework with rigorous theoretical guarantees, achieving asymptotic optimal editing performance while meeting the constraints of long-term knowledge preservation. Experimental results show that our framework scales sequential editing capacity to over 10,000 edits while stabilizing general capabilities and boosting average editing efficacy by 11.89% over SOTA baselines. Furthermore, it can be leveraged to enhance the performance of baseline methods. Our code is released on https://github.com/caskcsg/LyapLock.

Genglin Liu, Vivian T. Le, Salman Rahman, Elisa Kreiss, Marzyeh Ghassemi, Saadia Gabriel

We present a novel, open-source social network simulation framework, MOSAIC, where generative language agents predict user behaviors such as liking, sharing, and flagging content. This simulation combines LLM agents with a directed social graph to analyze emergent deception behaviors and gain a better understanding of how users determine the veracity of online social content. By constructing user representations from diverse fine-grained personas, our system enables multi-agent simulations that model content dissemination and engagement dynamics at scale. Within this framework, we evaluate three different content moderation strategies with simulated misinformation dissemination, and we find that they not only mitigate the spread of non-factual content but also increase user engagement. In addition, we analyze the trajectories of popular content in our simulations, and explore whether simulation agents’ articulated reasoning for their social interactions truly aligns with their collective engagement patterns.

Qihan Wang, Shidong Pan, Tal Linzen, Emily Black

Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingual prompting: a prompting method which generates several variations of a base prompt with added cultural and linguistic cues from several cultures, generates responses, and then combines the results. Building on evidence that LLMs have language-specific knowledge, multilingual prompting seeks to increase diversity by activating a broader range of cultural knowledge embedded in model training data. Through experiments across multiple models (GPT-4o, GPT-4o-mini, LLaMA 70B, and LLaMA 8B), we show that multilingual prompting consistently outperforms existing diversity-enhancing techniques such as high-temperature sampling, step-by-step recall, and persona prompting. Further analyses show that the benefits of multilingual prompting vary between high and low resource languages and across model sizes, and that aligning the prompting language with cultural cues reduces hallucination about culturally-specific information.

Justin Xu, Yiming Li, Zizheng Zhang, Augustine Yui Hei Luk, Mayank Jobanputra, Samarth Oza, Ashley Murray, Meghana Reddy Kasula, Andrew Parker, David W Eyre

Large language models (LLMs) can produce fluent but factually incorrect outputs and often have limited ability to attribute their claims to source material. This undermines their reliability, particularly in multi-hop and high-stakes domains such as medicine. We propose Tree-of-Quote (ToQ) prompting, a structured framework that decomposes complex questions into subquestions, generates quotes to support each step without retrieval, and selectively advances reasoning based on quote quality. We also introduce FQ-Score, a unified metric that captures answer correctness, attribution fidelity, and reasoning quality. Experiments on StrategyQA, 2WikiMultiHopQA, MuSiQue, MoreHopQA, and MedQA demonstrate that ToQ improves factuality and attribution over standard prompting baselines. To validate FQ-Score as a proxy for human judgment, we conduct two reader studies with clinicians on medical questions, and observe strong correlations. Both clinician scores and FQ-Scores also indicate a preference for ToQ over baselines due to a combination of greater correctness, completeness, and logical flow. Our results suggest ToQ is a promising approach for building more trustworthy and auditable LLM systems.

Yang Wu, Ruijia Wang, Jie Wu

Machine-generated text detection is critical for preventing misuse of large language models (LLMs). Although LLMs have recently excelled at mimicking human writing styles, they still suffer from factual hallucinations manifested as entity-relation inconsistencies with real-world knowledge. Current detection methods inadequately address the authenticity of the entity graph, which is a key discriminative feature for identifying machine-generated content. To bridge this gap, we propose a fact-aware model that assesses discrepancies between textual and factual entity graphs through graph comparison. In order to holistically analyze context information, our approach employs hierarchical feature extraction with gating units, enabling the adaptive fusion of multi-grained features from entity, sentence, and document levels. Experimental results on three public datasets demonstrate that our approach outperforms the state-of-the-art methods. Interpretability analysis shows that our model can capture the differences in entity graphs between machine-generated and human-written texts.

Hongxiang Zhang, Hao Chen, Muhao Chen, Tianyi Zhang

Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation. These methods typically operate at the token level, leveraging internal representations to suppress superficial patterns. Nevertheless, LLMs remain prone to hallucinations, especially over longer contexts. In this paper, we propose Active Layer-Contrastive Decoding (ActLCD), a novel decoding strategy that actively decides when to apply contrasting layers during generation. By casting decoding as a sequential decision-making problem, ActLCD employs a reinforcement learning policy guided by a reward-aware classifier to optimize factuality beyond the token level. Our experiments demonstrate that ActLCD surpasses state-of-the-art methods across five benchmarks, showcasing its effectiveness in mitigating hallucinations in diverse generation scenarios.

Shrey Pandit, Jiawei Xu, Junyuan Hong, Zhangyang Wang, Tianlong Chen, Kaidi Xu, Ying Ding

Advancements in Large Language Models (LLMs) and their increasing use in medical question-answering necessitate rigorous evaluation of their reliability. A critical challenge lies in hallucination, where models generate plausible yet factually incorrect outputs. In the medical domain, this poses serious risks to patient safety and clinical decision-making. To address this, we introduce MedHallu, one of the the first benchmark specifically designed for medical hallucination detection. MedHallu comprises 10,000 high-quality question-answer pairs derived from PubMedQA, with hallucinated answers systematically generated through a controlled pipeline. Our experiments show that state-of-the-art LLMs, including GPT-4o, Llama-3.1, and the medically fine-tuned UltraMedical, struggle with this binary hallucination detection task, with the best model achieving an F1 score as low as 0.625 for detecting ”hard” category hallucinations. Using bidirectional entailment clustering, we show that harder-to-detect hallucinations are semantically closer to ground truth. Through experiments, we also show incorporating domain-specific knowledge and introducing a ”not sure” category as one of the answer categories improves the precision and F1 scores by up to 38% relative to baselines.

Yiran Yang, Haifeng Sun, Jingyu Wang, Qi Qi, Zirui Zhuang, Huazheng Wang, Pengfei Ren, Jing Wang, Jianxin Liao

Existing research in multi-hop questions has identified two reasoning modes: latent reasoning and factual shortcuts, but has not deeply investigated how these modes differ during inference. This impacts both model generalization ability and downstream reasoning tasks. In this work, we systematically examine these distinctions and propose a simple and efficient classification metric, Attribute Rate Ratio (ARR). First, we construct specialized datasets corresponding to the two reasoning modes based on our proposed criteria. Then, using reverse engineering methods, including attention knockout and logit lens techniques, we reveal that subject representations differ significantly across modes: latent reasoning encodes bridge-related information for final answer extraction, while factual shortcuts bypass intermediate reasoning and resemble single-hop factual queries. Finally, our proposed ARR achieves around 90% accuracy on our datasets and demonstrates effectiveness in RAG conflict scenarios, showing that model behavior under conflicting prompts is closely tied to its underlying reasoning mode. Our findings and proposed metric have significant potential for advancing LLM development and applications.

Tian Lan, Jiang Li, Yemin Wang, Xu Liu, Xiangdong Su, Guanglai Gao

With the growing adoption of large language models (LLMs) in NLP tasks, concerns about their fairness have intensified. Yet, most existing fairness benchmarks rely on closed-ended evaluation formats, which diverge from real-world open-ended interactions. These formats are prone to position bias and introduce a “minimum score” effect, where models can earn partial credit simply by guessing. Moreover, such benchmarks often overlook factuality considerations rooted in historical, social, physiological, and cultural contexts, and rarely account for intersectional biases. To address these limitations, we propose F²Bench: an open-ended fairness evaluation benchmark for LLMs that explicitly incorporates factuality considerations. F²Bench comprises 2,568 instances across 10 demographic groups and two open-ended tasks. By integrating text generation, multi-turn reasoning, and factual grounding, F²Bench aims to more accurately reflect the complexities of real-world model usage. We conduct a comprehensive evaluation of several LLMs across different series and parameter sizes. Our results reveal that all models exhibit varying degrees of fairness issues. We further compare open-ended and closed-ended evaluations, analyze model-specific disparities, and provide actionable recommendations for future model development. Our code and dataset are publicly available at https://github.com/VelikayaScarlet/F2Bench.

PeiFeng Wang, Austin Xu, Yilun Zhou, Caiming Xiong, Shafiq Joty

To meet the increasing need for timely and accurate evaluation of large language model (LLM) responses, training LLM-as-judges to evaluate and critique other model responses has emerged as a popular paradigm. However, existing judge models are largely trained with supervised finetuning (SFT) on small data scales to perform limited types of evaluation tasks, fundamentally limiting generalization.To meet the need for strong, generalized judge models, we explore training foundational judge models at large data scales (680K) with direct preference optimization (DPO). Using four training tasks, we form three types of DPO preference pairs targeting different aspects of evaluation: Generating meaningful critiques, making accurate judgements, and understanding what comprises good and bad responses. To demonstrate the effectiveness of our method, we train judge models of three sizes: 8B parameters, 12B, and 70B, and evaluate on a comprehensive suite of 13 benchmarks (7 pairwise, 4 single rating, and 2 classification). Our models achieve the best aggregate performance, with even our 8B model outperforming GPT-4o in pairwise benchmarks. Further analysis shows that our judge models produce factual and actionable critiques and serve as strong foundational judges for continued finetuning.

Dustin Wright, Zain Muhammad Mujahid, Lu Wang, Isabelle Augenstein, David Jurgens

Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query, and extracting and citing evidence spans helps improve the trustworthiness of these summaries. Whereas previous work has focused on evidence citation with fixed levels of granularity (e.g. sentence, paragraph, document, etc.), we propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case. We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be “lost-in-the-middle”. To help models perform this task, we create the Summaries with Unstructured Evidence Text dataset (SUnsET), a synthetic dataset generated using a novel pipeline, which can be used as training supervision for unstructured evidence summarization. We demonstrate across 5 LLMs and 4 datasets spanning human written, synthetic, single, and multi-document settings that LLMs adapted with SUnsET generate more relevant and factually consistent evidence with their summaries, extract evidence from more diverse locations in their context, and can generate more relevant and consistent summaries than baselines with no fine-tuning and fixed granularity evidence. We release SUnsET and our generation code to the public (https://github.com/dwright37/unstructured-evidence-sunset).

Gregory Polyakov, Christian Hepting, Carsten Eickhoff, Seyed Ali Bahrainian

Large language models (LLMs) exhibit sophisticated behavior, notably solving arithmetic with only a few in-context examples (ICEs). Yet the computations that connect those examples to the answer remain opaque. We probe four open-weight LLMs, Pythia-12B, Llama-3.1-8B, MPT-7B, and OPT-6.7B, on basic arithmetic to illustrate how they process ICEs. Our study integrates activation patching, information-flow analysis, automatic circuit discovery, and the logit-lens perspective into a unified pipeline. Within this framework we isolate partial-sum representations in three-operand tasks, investigate their influence on final logits, and derive linear function vectors that characterize tasks and align with ICE-induced activations. Controlled ablations show that strict pattern consistency in the formatting of ICEs guides the models more strongly than the symbols chosen or even the factual correctness of the examples. By unifying four complementary interpretability tools, this work delivers one of the most comprehensive interpretability studies of LLM arithmetic to date, and the first on three-operand tasks. Our code is publicly available.

Xuemei Tang, Xufeng Duan, Zhenguang Cai

Large language models (LLMs) have emerged as a potential solution to automate the complex processes involved in writing literature reviews, such as literature collection, organization, and summarization. However, it is yet unclear how good LLMs are at automating comprehensive and reliable literature reviews. This study introduces a framework to automatically evaluate the performance of LLMs in three key tasks of literature review writing: reference generation, abstract writing, and literature review composition. We introduce multidimensional evaluation metrics that assess the hallucination rates in generated references and measure the semantic coverage and factual consistency of the literature summaries and compositions against human-written counterparts. The experimental results reveal that even the most advanced models still generate hallucinated references, despite recent progress. Moreover, we observe that the performance of different models varies across disciplines when it comes to writing literature reviews. These findings highlight the need for further research and development to improve the reliability of LLMs in automating academic literature reviews. The dataset and code used in this study are publicly available in our GitHub repository .

Teng Lin, Yuyu Luo, Honglin Zhang, Jicheng Zhang, Chunlin Liu, Kaishun Wu, Nan Tang

Cross-Document Multi-entity question answering (MEQA) demands the integration of scattered information across documents to resolve complex queries involving entities, relationships, and contextual dependencies. Although Large Language Models (LLMs) and Retrieval-augmented Generation (RAG) systems show promise, their performance on cross-document MEQA remains underexplored due to the absence of tailored benchmarks. To address this gap, we introduce MEBench, a scalable multi-document, multi-entity benchmark designed to systematically evaluate LLMs’ capacity to retrieve, consolidate, and reason over scattered and dense information. Our benchmark comprises 4,780 questions which are systematically categorized into three primary categories: Comparative Reasoning, Statistical Reasoning and Relational Reasoning, further divided into eight distinct types, ensuring broad coverage of real-world multi-entity reasoning scenarios. Our experiments on state-of-the-art LLMs reveal critical limitations: even advanced models achieve only 59% accuracy on MEBench. Our benchmark emphasizes the importance of completeness and factual precision of information extraction in MEQA tasks, using Entity-Attributed F1 (EA-F1) metric for granular evaluation of entity-level correctness and attribution validity. MEBench not only highlights systemic weaknesses in current LLM frameworks but also provides a foundation for advancing robust, entity-aware QA architectures.

Ingroj Shrestha, Padmini Srinivasan

Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM’s outputs to desired distributions. For example, we might want to align a model with real-world distributions to support factual grounding. Thus, we define bias as deviation from a desired distribution, which may be an equal or real-world distribution, depending on application goals. We propose a weighted adaptive loss based fine-tuning method that aligns LLM’s gender–profession output distribution with the desired distribution, while preserving language modeling capability. Using 3 profession sets—male-dominated, female-dominated, and gender-balanced—derived from U.S. labor statistics (2024), we assess both our adaptive method for reflecting reality and a non-adaptive variant for equality. Across three masked language models, bias is observed under both distributions. We achieve near-complete mitigation under equality and 30–75% reduction under real-world settings. Autoregressive LLMs show no bias under equality but notable bias under real-world settings, with the Llama Instruct models (3.2-3B, 3.1-8B) achieving a 50–62% reduction.

Qingcheng Zeng, Weihao Xuan, Leyang Cui, Rob Voigt

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a clear capacity for valuable self-reflection, how this ability interacts with other model behaviors remains underexplored. We investigate this connection by analyzing verbalized confidence, how models articulate their certainty, as a lens into the nature of self-reflection in LRMs. We find that supervised fine-tuning on reasoning traces (i.e., distillation) and reinforcement learning can improve verbalized calibration in reasoning-intensive settings in a progressive, laddered fashion. However, our results also indicate that reasoning models may possess a diminished awareness of their own knowledge boundaries, as evidenced by significantly lower “I don’t know” response rates on factuality benchmarks. Moreover, we examine the relationship between verbalized confidence and reasoning chains, finding that models tend to express higher confidence when providing shorter or less elaborate reasoning. Our findings highlight how reasoning-oriented training can enhance performance in reasoning-centric tasks while potentially incurring a reasoning tax, a cost reflected in the model’s reduced ability to accurately recognize the limits of its own knowledge in small-scale models. More broadly, our work showcases how this erosion of knowledge boundaries can compromise model faithfulness, as models grow more confident without a commensurate understanding of when they should abstain.

Yihong Liu, Runsheng Chen, Lea Hirlimann, Ahmad Dawar Hakimi, Mingyang Wang, Amir Hossein Kargaran, Sascha Rothe, François Yvon, Hinrich Schuetze

In large language models (LLMs), certain neurons can store distinct pieces of knowledge learned during pretraining. While factual knowledge typically appears as a combination of relations and entities, it remains unclear whether some neurons focus on a relation itself – independent of any entity. We hypothesize such neurons detect a relation in the input text and guide generation involving such a relation. To investigate this, we study the LLama-2 family on a chosen set of relations, with a statistics-based method. Our experiments demonstrate the existence of relation-specific neurons. We measure the effect of selectively deactivating candidate neurons specific to relation r on the LLM’s ability to handle (1) facts involving relation r and (2) facts involving a different relation r' \neq r. With respect to their capacity for encoding relation information, we give evidence for the following three properties of relation-specific neurons. \textbf{(i) Neuron cumulativity.} Multiple neurons jointly contribute to processing facts involving relation r, with no single neuron fully encoding a fact in r on its own. \textbf{(ii) Neuron versatility.} Neurons can be shared across multiple closely related as well as less related relations. In addition, some relation neurons transfer across languages. \textbf{(iii) Neuron interference.} Deactivating neurons specific to one relation can improve LLMs’ factual recall performance for facts of other relations. We make our code and data publicly available at https://github.com/cisnlp/relation-specific-neurons.