Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where conventional metrics struggle with input length limitations and long-range dependencies. In this work, we systematically evaluate the reliability of six widely used reference-free factuality metrics, originally proposed for short-form summarization, in the long-document setting. We probe metric robustness through seven factuality-preserving perturbations applied to summaries, namely paraphrasing, simplification, synonym replacement, logically equivalent negations, vocabulary reduction, compression, and source text insertion, and further analyze their sensitivity to retrieval context and claim information density. Across three long-form benchmark datasets spanning science fiction, legal, and scientific domains, our results reveal that existing short-form metrics produce inconsistent scores for semantically equivalent summaries and exhibit declining reliability for information-dense claims whose content is semantically similar to many parts of the source document. While expanding the retrieval context improves stability in some domains, no metric consistently maintains factual alignment under long-context conditions. Finally, our results highlight concrete directions for improving factuality evaluation, including multi-span reasoning, context-aware calibration, and training on meaning-preserving variations to enhance robustness in long-form summarization.
论文检索
输入标题、作者或关键词，从 1,386 篇学术成果中精准定位
Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users assess the correctness of generated outputs. Existing metrics using entailment classifiers require dataset-specific threshold tuning, while LLM-based approaches often use direct prompting, which underutilises the reasoning capabilities of LLMs. We address this by formulating grounded claim factuality checking as a true/false reading comprehension task and prompting LLMs with explicit test-taking strategies for efficient reasoning. Our method reduces token usage by over 80% compared to unguided open-ended reasoning, and achieves competitive performance to more expensive alternatives across two factuality benchmarks, setting a new state of the art on one. To further reduce inference cost, we train small language models (SLMs) to replace LLMs in the checking pipeline. Using supervised fine-tuning (SFT) and a self-revision mechanism, the SLMs learn to improve their factuality judgements. Experimental results show that the resulting SLMs perform on par with strong baselines, combining low inference costs with generating supporting rationales to support interpretability. Code and datasets will be released upon acceptance.
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
PDF ↗Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that validate users rather than prioritize factual accuracy. While prior work has established that sycophancy poses risks to AI safety and alignment, the relationship between specific personality traits of adopted personas and the degree of sycophantic behavior remains unexplored. We present a systematic investigation of how persona agreeableness influences sycophancy across 13 small, open-weight language models ranging from 0.6B to 20B parameters. We develop a benchmark comprising 275 personas evaluated on NEO-IPIP agreeableness subscales and expose each persona to 4,950 sycophancy-eliciting prompts spanning 33 topic categories. Our analysis reveals that 9 of 13 models exhibit statistically significant positive correlations between persona agreeableness and sycophancy rates, with Pearson correlations reaching r = 0.87 and effect sizes as large as Cohen’s d = 2.33. These findings demonstrate that agreeableness functions as a reliable predictor of persona-induced sycophancy, with direct implications for the deployment of role-playing AI systems and the development of alignment strategies that account for personality-mediated deceptive behaviors
Generating radiology reports from 3D volumetric data remains challenging due to the difficulty of grounding fine-grained pathologies within high-dimensional scans. While retrieval-augmented generation (RAG) offers a potential solution, standard approaches struggle with visual-semantic ambiguity and often introduce irrelevant "normal" context that dilutes pathological signals. To address this limitation, we introduce CPR-RAG, a model-agnostic RAG framework that enhances organ-level grounding by integrating clinical priors into the retrieval process. Specifically, we propose a clinical prior-regularized re-ranking module that leverages corpus-derived co-occurrence statistics to align retrieved candidates with latent disease distributions, ensuring clinical consistency beyond mere visual similarity. Furthermore, we employ clinical relevance context refinement to selectively filter out boilerplate normal descriptions, thereby maximizing the information density of the evidence provided to the generator. Extensive experiments on the RadGenome-ChestCT benchmark demonstrate that CPR-RAG significantly improves clinical efficacy across state-of-the-art radiology report generation models. Human evaluation further confirms that our approach achieves superior factual correctness, completeness, and utility compared to the existing models.
Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present Knowme-Bench, a publicly releasable benchmark built from long-form autobiographical narratives, where actions, context, and inner thoughts provide dense evidence for inferring stable motivations and decision principles. Knowme-Bench reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning. Across diverse narrative sources, retrieval-augmented systems mainly improve factual accuracy, while errors persist on temporally grounded explanations and higher-level inferences, highlighting the need for memory mechanisms beyond retrieval.
Training expert LLMs in domains with scarce fine-grained annotated data is admittedly challenging, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While outcome-based RL may improve accuracy, it frequently compromises the reasoning process, yielding internally inconsistent rationales that diverge from the final predictions. Existing solutions to supervise the reasoning process, such as large-scale Process Reward Models (PRMs), are prohibitively expensive. To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using a small, general-purpose LLM only. CLARity integrates a consistency-aware reward mechanism with a 2-stage refine-then-monitor training pipeline to enhance reasoning consistency, and a dynamic data reformulation strategy to better exploit annotated data available. Experiments demonstrate that CLARity can improve the consistency of responses by 16.5% over standard outcome-based RL, and bring an improvement of 7.5% in final accuracy. Human evaluations further confirm substantial gains in factual correctness and reasoning coherence, leading to more trustworthy model outputs. Thus, CLARity offers a generalizable solution that enables smaller models to effectively guide expert LLM training by monitoring reasoning consistency.
LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction
PDF ↗Knowledge graphs (KGs) provide a structured representation of real-world facts as triples consisting of entities and their relationships. With the rapid progress of large language models (LLMs), recent studies increasingly explore LLMs for end-to-end KG construction from text. In particular, generative knowledge extraction (GKE) builds KGs by directly generating structured triples from documents. However, generation errors are inevitable, and the resulting KGs often contain triples that do not align with the facts expressed in the source text. To address these issues, we propose GraphRefine, a framework that performs triple-level refinement on KGs constructed via GKE. We first analyze factual inconsistencies that arise in GKE and categorize their types based on a human evaluation. We then construct training data reflecting these types and fine-tune an LLM as a KG refiner. Given a draft KG, the fine-tuned refiner selects a refinement operation for each triple and, if needed, deletes, edits, or rewrites it to reduce factual inconsistencies. Extensive experiments demonstrate that GraphRefine goes beyond deletion-only approaches and improves KG quality from diverse perspectives.
Interleaved multimodal understanding and generation—where models can interactively comprehend and produce images and text in arbitrary orders—has emerged as a key research direction in generative Multimodal Large Language Models(MLLMs). Such interleaved image–text content plays an increasingly important role in information dissemination. However, the compounded persuasive power of multimodal narratives also raises the risk of factual misinformation. Despite this, existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image–text content. To bridge this gap, we introduce FactVerse, a benchmark dedicated to evaluating factual consistency in interleaved image-text generation. FactVerse comprises 3,000 human-verified instances across four categories and 50 domains, supporting both English and Chinese. We also establish a multi-dimensional evaluation framework designed to rigorously assess factual consistency. Experiments demonstrate that our framework achieves high alignment with human judgments, significantly outperforming existing evaluation methods. Furthermore, our analysis reveals systematic deficiencies in current models, offering critical insights for future design.
First-order logic (FOL) is a fundamental formalism for factual reasoning over knowledge graphs (KGs), e.g. in researches of KG-based fact verification and logical consistency or reasoning of large language models (LLM). However, existing benchmarks and approaches insufficiently capture many claims that require comparison or counting, and lack support for several FOL quantifiers and connectives. To address these challenges and expand the expressive capacity of FOL for KG-based reasoning, we introduce FOLX-KG, a novel extended FOL \sigma-structure over KGs that incorporates comparison predicates and counting quantifiers. Using this extended logic, we construct Fact-FOLX-KG, a fact verification dataset consisting of 43,821 KG-based claim–formula pairs designed to enable systematic study of richer logical forms and reasoning types. We further propose FOLX Prover, an executable program-guided logic reasoning pipeline adapted for KG-based factual reasoning under the extended FOL. Experimental results show that our method achieves state-of-the-art performance on Fact-FOLX-KG, while previous methods experience performance drop on claims requiring comparison and counting. These findings demonstrate the importance of extended logical expressiveness for robust factual reasoning over KGs.
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training
PDF ↗The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training. We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy. SMI is validated through large-scale document retrieval over the disclosed pre-training corpora of 21 public and 3 custom models, combined with a robust multi-template QA evaluation. Experiments show that SMI significantly outperforms repetition-based baselines and achieves R² > 0.7 in predicting QA accuracy for models above 1B parameters, without additional training. The analysis further reveals diminishing returns from scaling data and model size and provides evidence for an intrinsic upper bound on knowledge retention achievable by pre-training alone, motivating retrieval and other augmentation strategies.
Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
PDF ↗Retrieval-Augmented Generation (RAG) has become a key paradigm for reducing factual hallucinations in Large Language Models (LLMs), yet little is known about how the order of retrieved documents affects model behavior. We empirically show that under a Top-5 retrieval setting with the gold document included, LLM answers vary substantially across permutations of the retrieved set, even when the gold document is fixed in the first position. This reveals a previously underexplored sensitivity to retrieval permutations. Although existing robust RAG methods focus primarily on enhancing LLM robustness to low-quality retrieval and mitigating positional bias to distribute attention fairly over long contexts, neither approach directly addresses permutation sensitivity. In this paper, we propose Stable-RAG, which exploits permutation sensitivity estimation to mitigate permutation-induced hallucinations. Stable-RAG runs the generator under multiple retrieval orders, clusters hidden states, and decodes from a cluster-center representation that captures the dominant reasoning pattern. It then uses these reasoning results to align hallucinated outputs toward the correct answer, encouraging the model to produce consistent and accurate predictions across document permutations. Experiments on three QA datasets show that Stable-RAG improves answer accuracy, reasoning consistency, and generalization across datasets, retrievers, and input lengths compared with strong baselines.
Retrieval-Augmented Generation (RAG) is a mainstream approach to mitigating hallucinations in Large Language Models (LLMs), yet in dynamic real-world scenarios, such as weather forecasting or evolving news events, existing retrievers suffer from both temporal-semantic misalignment and outdated-document interference. To address this, we propose Relevance Recency Retrieval (Re^3), a novel framework that mitigates temporal hallucinations via two core components: a Time-Aware Dual Relevance Encoder that embeds heterogeneous temporal signals into the semantic space to ensure retrieval fidelity, and a Conflict-Aware Recency Filter that performs listwise arbitration to identify and suppress obsolete factual versions. To rigorously evaluate this setting, we introduce Re^2 Bench, a large-scale benchmark comprising over 1.3 million instances designed to assess system robustness in realistic environments where temporal constraints and conflicting factual versions coexist. Experiments on three public benchmarks and Re^2 Bench demonstrate that Re^3 consistently outperforms the strongest baselines by an average of 9.7% in generation accuracy, with gains of up to 25.2% on challenging dynamic tasks, while demonstrating robustness across diverse RAG settings.
Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise goals. We introduce VLN-NF, a benchmark with false-premise instructions where the target is absent from the specified area and agents must navigate, gather evidence through in-room exploration, and explicitly output NOT-FOUND. VLN-NF is constructed via a scalable pipeline that rewrites VLN instructions using an LLM and verifies target absence with a VLM, producing plausible yet factually incorrect goals. We further propose REV-SPL to jointly evaluate room reaching, exploration coverage, and decision correctness. To address this challenge, we present ROAM, a two-stage hybrid that combines supervised room-level navigation with LLM/VLM-driven in-room exploration guided by a free-space clearance prior. ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions. Code and data will be released upon acceptance.
Long-term conversational memory is a core capability for LLM-baseddialogue systems, yet existing benchmarks and evaluation protocolsprimarily focus on surface-level factual recall.In realistic interactions, appropriate responses often depend onimplicit constraints such as user state, goals, or values that are notexplicitly queried later.To evaluate this setting, we introduce LoCoMo-Plus, a benchmarkfor assessing cognitive memory under cue–trigger semantic disconnect,where models must retain and apply latent constraints across longconversational contexts.We further show that conventional string-matching metrics and explicittask-type prompting are misaligned with such scenarios, and propose aunified evaluation framework based on constraint consistency.Experiments across diverse backbone models, retrieval-based methods, andmemory systems demonstrate that cognitive memory remains challenging andreveals failures not captured by existing benchmarks.Our code and evaluation framework are publicly available at https://github.com/xjtuleeyf/Locomo-Plus.
Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: **(I) Poor generalization:** Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical problems. **(II) Narrow scope:** Current methods focus primarily on structured fact triples, overlooking the diverse unstructured forms of factual information (e.g., news, articles) prevalent in real-world contexts. To address these challenges, we propose a new paradigm: teaching LLMs to edit knowledge via **Chain of Thoughts** (CoTs) reasoning (CoT2Edit). We first leverage language model agents for both structured and unstructured edited data to generate CoTs, building high-quality instruction data. The model is then trained to reason over edited knowledge through supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). At inference time, we integrate Retrieval-Augmented Generation (RAG) to dynamically retrieve relevant edited facts for real-time knowledge editing. Experimental results demonstrate that our method achieves strong generalization across six diverse knowledge editing scenarios with **just a single round of training** on three open-source language models.
While Large Language Models (LLMs) exhibit strong semantic capabilities, their resilience to manipulative linguistic patterns such as logical fallacies remains an underexplored area. Prior work has focused on the ability of LLMs to **identify** or **classify** fallacies, but their robustness against these fallacies in persuasive contexts remains largely unexplored.To address this gap, we introduce **LoFa** (Logical Fallacy), a comprehensive benchmark to evaluate LLM robustness against fallacies. We first construct the **LoFa** dataset via a multi-agent pipeline, pairing factual questions with fallacious arguments. Then, we develop a multi-round debate framework to assess model resilience under sustained attacks.Furthermore, to disentangle robustness from a model’s inherent knowledge limitations, we propose a new metric, LFR@k (Logical Fallacy Resistance), to quantify performance. Our experiments reveal that different LLMs exhibit varied robustness to distinct types of fallacies, highlighting unique vulnerability profiles across models.
LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains
PDF ↗A criminal judicial opinion represents the judge’s disposition of a case, including the decision rationale and sentencing. Automatically generating such opinions can assist in analyzing sentencing consistency and provide judges with references to past similar cases. However, current research typically approaches this task by dividing it into two isolated subtasks: legal reasoning and sentencing prediction. This separation often leads to inconsistency between the reasoning and predictions, failing to meet real-world judicial requirements. Furthermore, prior studies rely on manually creating knowledge to enhance applicability, yet such methods remain limited in practical deployment. To address these limitations and better align with legal practice, we propose a new LegalAI task: Criminal Judicial Opinion Generation, which simultaneously produces both legal reasoning and sentencing decisions. To achieve this, we introduce LegalChainReasoner framework that applies structured legal chains to guide the model through comprehensive case assessments. By integrating factual premises, composite legal conditions, and sentencing conclusions, our approach ensures flexible knowledge injection and end-to-end opinion generation. Experiments on real-world, open-source Chinese legal case datasets demonstrate that our method outperforms baseline models.
Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA
PDF ↗To improve the reliability of Large Language Models (LLMs) in clinical applications, retrieval-augmented generation (RAG) is extensively applied to provide factual medical knowledge. However, beyond general medical knowledge from open-ended datasets, clinical case-based knowledge is also critical for effective medical reasoning, as it provides context grounded in real-world patient experiences. Motivated by this, we propose Experience Retrieval-Augmentation ExpRAG framework based on Electronic Health Record(EHR), aiming to offer the relevant context from other patients’ discharge reports. ExpRAG performs retrieval through a coarse-to-fine process, utilizing an EHR-based report ranker to efficiently identify similar patients, followed by an experience retriever to extract task-relevant content for enhanced medical reasoning. To evaluate ExpRAG, we introduce DischargeQA, a clinical QA dataset with 1,280 discharge-related questions across diagnosis, medication, and instruction tasks. Each problem is generated using EHR data to ensure realistic and challenging scenarios. Experimental results demonstrate that ExpRAG consistently outperforms a text-based ranker, achieving an average relative improvement of 5.2%, highlighting the importance of case-based knowledge for medical reasoning.
InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication
PDF ↗Insurance claims adjudication demands not only accurate decisions but also interpretable reasoning grounded in policy clauses. However, existing benchmarks are limited to information retrieval or simple multiple-choice setups, which fail to require step-by-step inferences from facts to conclusions. To address this gap, we introduce InsLogicBench, a benchmark providing complete reasoning traces that link factual inputs, relevant policy clauses, and final verdicts. We construct the dataset using a controllable synthesis framework based on the Nested Toulmin Model. By capturing the defeasible logic of insurance policies through hierarchical truth assignment and enforcing validity via consistency verification, we ensure interpretability and logical rigor across generated examples. We evaluate eight Large Language Models (LLMs) on InsLogicBench. Results show significant difficulties in handling exception clauses and verifying missing conditions. Notably, models often produce correct final decisions but fail to provide precise justifications, highlighting a critical discrepancy between their decision accuracy and logical reasoning capabilities.
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
PDF ↗Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to **open-domain settings** remains a critical challenge, as **unconstrained generation** entails multi-faceted and often conflicting objectives—such as creativity versus factuality—where rigid, static reward scalarization is inherently suboptimal. To address this, we propose **MAESTRO** (**M**eta-learning **A**daptive **E**stimation of **S**calarization **T**rade-offs for **R**eward **O**ptimization), which introduces a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as a semantic bottleneck to perceive task-specific priorities. We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal. Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines, while preserving the efficiency advantages of GRPO, and in some settings even reducing redundant generation.