论文检索

Daiqing Qi, Handong Zhao, Jing Shi, Simon Jenni, Yifei Fan, Franck Dernoncourt, Scott Cohen, Sheng Li

Photographer, curator, and former director of photography at the Museum of Modern Art (MoMA), John Szarkowski remarked in *William Eggleston's Guide*, "While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky." Szarkowski insightfully revealed a notable gap between general and aesthetic visual understanding: while the former emphasizes identifying factual elements in an image (the sky), the latter transcends mere object identification, viewing it instead as an aesthetic component--a pure expanse of blue, valued purely as a color block in visual aesthetics. Such distinctions between general visual understanding (detection, localization, etc.) and aesthetic perception (color, lighting, composition, etc.) pose a significant challenge for existing Multimodal Large Language Models (MLLMs) in comprehending image aesthetics, which is increasingly needed in real-world applications, from image recommendation and enhancement to generation. To fundamentally advance the aesthetic understanding of MLLMs, we introduce a novel dataset, PhotoCritique, derived from extensive discussions among professional photographers and enthusiasts, distinguished by its large scale, expertise, and diversity. Additionally, we propose a new model, PhotoEye, an MLLM featuring a language-guided multi-view vision fusion mechanism for understanding image aesthetics from multiple perspectives. Finally, we introduce PhotoBench, a comprehensive and professional benchmark for aesthetic visual understanding. Our model demonstrates significant advantages over both open-source and commercial models on existing benchmarks and PhotoBench.

Yuanchen Wu, Lu Zhang, Hang Yao, Junlong Du, Ke Yan, Shouhong Ding, Yunsheng Wu, Xiaoqiang Li

Large Vision-Language Models (LVLMs) have achieved impressive results across various cross-modal tasks. However, hallucinations, i.e., the models generating counterfactual responses, remain a challenge. Though recent studies have attempted to alleviate object perception hallucinations, they focus on the models' response generation, and overlook the task question itself. This paper discusses the vulnerability of LVLMs in solving counterfactual presupposition questions (CPQs), where the models are prone to accept the presuppositions of counterfactual objects and produce severe hallucinatory responses. To this end, we introduce "Antidote", a unified, synthetic data-driven post-training framework for mitigating both types of hallucination above. It leverages synthetic data to incorporate factual priors into questions to achieve self-correction, and decouples the mitigation process into a preference optimization problem. Furthermore, we construct "CP-Bench", a novel benchmark to evaluate LVLMs' ability to correctly handle CPQs and produce factual responses. Applied to the LLaVA series, Antidote can simultaneously enhance performance on CP-Bench by over 50%, POPE by 1.8-3.3%, and CHAIR & SHR by 30-50%, all without relying on external supervision from stronger LVLMs or human feedback and without introducing noticeable catastrophic forgetting issues.

Jinwoo Kim, Sangmin Han, Jinho Jeong, Jiwoo Choi, Dongyeoung Kim, Seon Joo Kim

Object compositing, the task of placing and harmonizing objects in images of diverse visual scenes, has become an important task in computer vision with the rise of generative models.However, existing datasets lack the diversity and scale required to comprehensively explore real-world scenarios comprehensively. We introduce ORIDa (Object-centric Real-world Image Composition Dataset), a large-scale, real-captured dataset containing over 30,000 images featuring 200 unique objects, each of which is presented across varied positions and scenes. ORIDa has two types of data: factual-counterfactual sets and factual-only scenes. The factual-counterfactual sets consist of four factual images showing an object in different positions within a scene and a single counterfactual (or background) image of the scene without the object, resulting in five images per scene. The factual-only scenes include a single image containing an object in a specific context, expanding the variety of environments. To our knowledge, ORIDa is the first publicly available dataset with its scale and complexity for real-world image composition. Extensive analysis and experiments highlight the value of ORIDa as a resource for advancing further research in object compositing.

Yajing Yang, Tony Deng, Min-Yen Kan

We propose KAHAN, a knowledge-augmented hierarchical framework that systematically extracts insights from raw tabular data at entity, pairwise, group, and system levels. KAHAN uniquely leverages LLMs as domain experts to drive the analysis. On DataTales financial reporting benchmark, KAHAN outperforms existing approaches by over 20% on narrative quality (GPT-4o), maintains 98.2% factuality, and demonstrates practical utility in human evaluation. Our results reveal that knowledge quality drives model performance through distillation, hierarchical analysis benefits vary with market complexity, and the framework transfers effectively to healthcare domains. The data and code are available at https://github.com/yajingyang/kahan.

Melika Nobakhtian, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

Allusion recognition—a task demanding contextual activation of cultural knowledge—serves as a critical test of LLMs’ ability to deploy stored information in open-ended, figurative settings. We introduce a framework for evaluating Persian literary allusions through (1) classical poetry annotations and (2) LLM-generated texts incorporating allusions in novel contexts. By combining knowledge assessments, multiple-choice tasks, and open-ended recognition, we analyze whether failures stem from knowledge gaps or activation challenges. Evaluations across eleven LLMs highlight a notable observation: models exhibit strong foundational knowledge and high multiple-choice accuracy, yet performance drops substantially in open-ended tasks, especially for indirect references. Reasoning-optimized models generalize better to novel contexts, whereas distilled models show marked degradation in cultural reasoning. The gap underscores that LLMs’ limitations arise not from missing knowledge but from difficulties in spontaneously activating cultural references without explicit cues. We propose allusion recognition as a benchmark for contextual knowledge deployment, highlighting the need for training paradigms that bridge factual recall and culturally grounded reasoning. Our code, datasets and results are available at https://github.com/MelikaNobakhtian/Allusion

Changmao Li, Jeffrey Flanigan

Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective low-latency post-correction method, Retrieval Augmented Correction (RAC), aimed at enhancing the factual performance of LLMs without requiring additional fine-tuning. Our method is general and can be used with any instruction-tuned LLM, and has greatly reduced latency compared to prior approaches. RAC decomposes the LLM’s output into atomic facts and applies a fine-grained verification and correction process with retrieved content to verify and correct the LLM-generated output. Our extensive experiments show that RAC yields up to 30% improvements over the LLM baselines across three popular factuality evaluation datasets, validating its efficacy and robustness with and without the integration of Retrieval-Augmented Generation (RAG) across different LLMs. Notably, our method has reduced latency up to 40x and reduced token consumption up to 7x compared to previous state-of-the-art post-correction approaches with similar or better performance.

Woojun Jung, Junyeong Kim

Video-to-text summarization remains underexplored in terms of comprehensive evaluation methods. Traditional n-gram overlap-based metrics and recent large language model (LLM)-based approaches depend heavily on human-written reference summaries, limiting their practicality and sensitivity to nuanced semantic aspects. In this paper, we propose QEVA, a reference-free metric evaluating candidate summaries directly against source videos through multimodal question answering. QEVA assesses summaries along three clear dimensions: Coverage, Factuality, and Temporal Coherence. We also introduce MLVU(VS)-Eval, a new annotated benchmark derived from the MLVU dataset, comprising 800 summaries generated from 200 videos using state-of-the-art video-language multimodal models. This dataset establishes a transparent and consistent framework for evaluation. Experimental results demonstrate that QEVA shows higher correlation with human judgments compared to existing approaches, as measured by Kendall’s \tau_b, \tau_c, and Spearman’s \rho. We hope that our benchmark and metric will facilitate meaningful progress in video-to-text summarization research and provide valuable insights for the development of future evaluation methods.

Lingnan Xu, Chong Feng, Kaiyuan Zhang, Liu Zhengyong, Wenqiang Xu, Fanqing Meng

While large language models (LLMs) demonstrate impressive capabilities, their reliance on parametric knowledge often leads to factual inaccuracies. Retrieval-Augmented Generation (RAG) mitigates this by leveraging external documents, yet existing approaches treat retrieved passages as isolated chunks, ignoring valuable structure that is crucial for document organization. Motivated by this gap, we propose Retrieve-DocumentRoute-Read (RDR2), a novel framework that explicitly incorporates structural information throughout the RAG process. RDR2 employs an LLM-based router to dynamically navigate document structure trees, jointly evaluating content relevance and hierarchical relationships to assemble optimal evidence. Our key innovation lies in formulating document routing as a trainable task, with automatic action curation and structure-aware passage selection inspired by human reading strategies. Through comprehensive evaluation on five challenging datasets, RDR2 achieves state-of-the-art performance, demonstrating that explicit structural awareness significantly enhances RAG systems’ ability to acquire and utilize knowledge, particularly in complex scenarios requiring multi-document synthesis.

Qin Hua, Jiaqi Sun, Shiyou Qian, Dingyu Yang, Jian Cao, Guangtao Xue

Knowledge-based complex reasoning remains a significant challenge for large language models (LLMs) with in-context learning. To tackle this issue, previous studies focus on ensuring behavior fidelity, factuality, or reliability in generated reasoning processes that guide LLMs to produce solutions. However, these studies often neglect the simultaneous optimization on all these three aspects for each thought. The main challenges are the lack of comprehensive assessment mechanisms and the difficulty of efficient thought-level optimization. This paper introduces the Evolution of Thoughts (EoT) framework, which enhances the factuality, fidelity, and reliability of each thought in the reasoning process through a few LLM inferences. We propose a thought assessment method that is sensitive to knowledge and LLM behaviors, using three scorers to evaluate each thought by considering domain context, semantic alignment, and behavior impact. Additionally, we establish a self-reflective evolution mechanism to facilitate each reasoning process generation in a single-forward inference. Extensive experiments demonstrate that, for knowledge-based complex tasks, EoT improves the factuality and fidelity of reasoning processes by approximately 16.5% and 48.8%, respectively, while enhancing LLM reasoning capability by about 6.2%, outperforming advanced approaches.

Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu 等

Evaluating the factuality of long-form generations from Large Language Models (LLMs) remains challenging due to accuracy issues and costly human assessment. Prior evaluation pipelines attempt this by decomposing text into claims, searching for evidence, and verifying claims, but suffer from critical drawbacks: (1) inefficiency due to complex pipeline components unsuitable for long LLM outputs, and (2) ineffectiveness stemming from inaccurate claim sets and insufficient evidence collection of one-line SERP snippets. To address these limitations, we adapt the existing decompose-then-verify evaluation framework and propose **FaStFact**, a fast and strong evaluation pipeline that achieves the highest alignment with human evaluation and efficiency among existing baselines. FaStFact first employs chunk-level claim extraction integrated with confidence-based pre-verification, significantly reducing the cost of web searching and inference calling while ensuring reliability. For searching and verification, it gathers document-level evidence from crawled website pages for retrieval during verification, addressing the evidence insufficiency problem in previous pipelines. Extensive experiments based on an aggregated and manually annotated benchmark demonstrate the reliability of FaStFact in both efficiently and effectively evaluating the factuality of long-form LLM generations. We submit the paper with code and benchmark, and will make them publicly available to facilitate research.

Sarfraz Ahmad, Hasan Iqbal, Momina Ahsan, Numaan Naeem, Muhammad Ahsan Riaz Khan, Arham Riaz, Muhammad Arslan Manzoor, Yuxia Wang, Preslav Nakov

The rapid adoption of Large Language Models (LLMs) has raised important concerns about the factual reliability of their outputs, particularly in low-resource languages such as Urdu. Existing automated fact-checking systems are predominantly developed for English, leaving a significant gap for the more than 200 million Urdu speakers worldwide. In this work, we present UrduFactBench and UrduFactQA, two novel hand-annotated benchmarks designed to enable fact-checking and factual consistency evaluation in Urdu. While UrduFactBench focuses on claim verification, UrduFactQA targets the factuality of LLMs in question answering. These resources, the first of their kind for Urdu, were developed through a multi-stage annotation process involving native Urdu speakers. To complement these benchmarks, we introduce UrduFactCheck, a modular fact-checking framework that incorporates both monolingual and translation-based evidence retrieval strategies to mitigate the scarcity of high-quality Urdu evidence. Leveraging these resources, we conduct an extensive evaluation of twelve LLMs and demonstrate that translation-augmented pipelines consistently enhance performance compared to monolingual ones. Our findings reveal persistent challenges for open-source LLMs in Urdu and underscore the importance of developing targeted resources. All code and data are publicly available at https://github.com/mbzuai-nlp/UrduFactCheck.

Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu, Ahmed Alaa, Thomas Hartvigsen, Gopala Anumanchipalli

Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this paper, we formalize the popular locate-then-edit methods as a two-step fine-tuning process, allowing us to precisely identify the root cause of this degradation. We show that model degradation occurs due to (1) over-optimization of internal activations and (2) continuous norm-growth of edited matrices. To mitigate these issues, we introduce two regularization techniques: (1) Most-Probable Early Stopping (MPES) and (2) explicit Frobenius norm-constraint. We demonstrate that applying these simple yet effective regularization techniques at key points in the editing process can substantially mitigate model degradation. Combining these regularization methods enables scaling locate-then-edit methods to 10,000 edits while reducing editing time by 42-61%. These results show that targeted regularization is essential for lifelong knowledge editing.

Sangyeop Kim, Yohan Lee, Sanghwa Kim, Hyunjong Kim, Sungzoon Cho

Effective long-term memory in conversational AI requires synthesizing information across multiple sessions. However, current systems place excessive reasoning burden on response generation, making performance significantly dependent on model sizes. We introduce PREMem (Pre-storage Reasoning for Episodic Memory), a novel approach that shifts complex reasoning processes from inference to memory construction. PREMem extracts fine-grained memory fragments categorized into factual, experiential, and subjective information; it then establishes explicit relationships between memory items across sessions, capturing evolution patterns like extensions, transformations, and implications. By performing this reasoning during pre-storage rather than when generating a response, PREMem creates enriched representations while reducing computational demands during interactions. Experiments show significant performance improvements across all model sizes, with smaller models achieving results comparable to much larger baselines while maintaining effectiveness even with constrained token budgets. Code and dataset are available at https://github.com/sangyeop-kim/PREMem.

Manan Roy Choudhury, Anirudh Iyengar Kaniyar Narayana Iyengar, Shikhhar Siingh, Sugeeth Puranam, Vivek Gupta

We study the capabilities of large language models (LLMs) in detecting fine-grained anomalies in tabular data. Specifically, we examine: (1) how well LLMs can identify diverse anomaly types including factual, logical, temporal, and value-based errors; (2) the impact of prompt design and prompting strategies; and (3) the effect of table structure and anomaly type on detection accuracy. To this end, we introduce TABARD, a new benchmark constructed by perturbing tables from WikiTQ, FeTaQA, Spider, and BEAVER. The dataset spans multiple domains and eight anomaly categories, including paired clean and corrupted tables. We evaluate LLMs using direct, indirect, and Chain-of-Thought (CoT) prompting. Our results reveal notable limitations in standard prompting, especially for complex reasoning tasks and longer tables. To overcome these issues, we propose a unified framework combining multi-step prompting, self-verification, and constraint-based rule execution. Our approach significantly improves precision and recall, offering a promising direction for robust and interpretable anomaly detection in tables.

Madhav Krishan Garg, Tejash Prasad, Tanmay Singhal, Chhavi Kirtani, Murari Mandal, Dhruv Kumar

The escalating volume of academic research, coupled with a shortage of qualified reviewers, necessitates innovative approaches to peer review. In this work, we propose: (1) ReviewEval, a comprehensive evaluation framework for AI-generated reviews that measures alignment with human assessments, verifies factual accuracy, assesses analytical depth, identifies degree of constructiveness and adherence to reviewer guidelines; and (2) ReviewAgent, an LLM-based review generation agent featuring a novel alignment mechanism to tailor feedback to target conferences and journals, along with a self-refinement loop that iteratively optimizes its intermediate outputs and an external improvement loop using ReviewEval to improve upon the final reviews. ReviewAgent improves actionable insights by 6.78% and 47.62% over existing AI baselines and expert reviews respectively. Further, it boosts analytical depth by 3.97% and 12.73%, enhances adherence to guidelines by 10.11% and 47.26% respectively. This paper establishes essential metrics for AI-based peer review and substantially enhances the reliability and impact of AI-generated reviews in academic research.

Monika Wysoczańska, Shyamal Buch, Anurag Arnab, Cordelia Schmid

Large vision-language models (VLMs) often struggle to generate long and factual captions. However, traditional measures for hallucination and factuality are not well suited for evaluating longer, more diverse captions and in settings where ground-truth human-annotated captions are unavailable. We introduce OVFact, a novel method for measuring caption factuality of long captions that leverages open-vocabulary visual grounding and tool-based verification without depending on human annotations. Our method improves agreement with human judgements and captures both caption descriptiveness (recall) and factual precision in the same metric. Furthermore, unlike previous metrics, our reference-free method design enables new applications towards factuality-based data filtering. We observe models trained on an OVFact-filtered (2.5-5x less) subset of a large-scale, noisy (VLM-generated) pretraining set meaningfully improve factuality precision without sacrificing caption descriptiveness across a range of downstream long caption benchmarks.

Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong 等

Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge to improve factuality. However, existing RAG systems frequently underutilize the retrieved documents, failing to extract and integrate the key clues needed to support faithful and interpretable reasoning, especially in cases where relevant evidence is implicit, scattered, or obscured by noise. To address this issue, we propose ClueAnchor, a novel framework for enhancing RAG via clue-anchored reasoning exploration and optimization. ClueAnchor extracts key clues from retrieved content and generates multiple reasoning paths based on different knowledge configurations, optimizing the model by selecting the most appropriate reasoning path for the given context through reward-based preference optimization. Experiments show that ClueAnchor significantly outperforms prior RAG baselines in the completeness and robustness of reasoning. Further analysis confirms its strong resilience to noisy or partially relevant retrieved content, as well as its capability to identify supporting evidence even in the absence of explicit clue supervision during inference. All codes are available at https://github.com/thunlp/ClueAnchor.

Atharva Kulkarni, Yuan Zhang, Joel Ruben Antony Moniz, Xiou Ge, Bo-Hsiang Tseng, Dhivya Piraviperumal, Swabha Swayamdipta, Hong Yu

Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many task- and domain-specific metrics have been proposed to assess faithfulness and factuality concerns, the robustness and generalization of these metrics are still untested. In this paper, we conduct a large-scale empirical evaluation of 6 diverse sets of hallucination detection metrics across 4 datasets, 37 language models from 5 families, and 5 decoding methods. Our extensive investigation reveals concerning gaps in current hallucination evaluation: metrics often fail to align with human judgments, take an overtly myopic view of the problem, and show inconsistent gains with parameter scaling. Encouragingly, LLM-based evaluation, particularly with GPT-4, yields the best overall results, and mode-seeking decoding methods seem to reduce hallucinations, especially in knowledge-grounded settings. These findings underscore the need for more robust metrics to understand and quantify hallucinations, and better strategies to mitigate them.

Wei Chen, Zhi Zheng, Lili Zhao, Huijun Hou, Tong Xu

Multi-hop question answering is a challenging task that requires capturing information from different positions in multiple documents. Recently, several methods propose to enhance Large Language Models (LLMs) by incorporating structured knowledge, aiming to grasp key information for solving this task. Despite certain achievements, they still face the following challenges: 1) The neglect of text-based reasoning capabilities. 2) Information redundancy between text and triples. 3) Information loss during structured knowledge extraction. To solve the above challenges, in this paper, we propose Dynamic Combination of Structured Knowledge (DCSK), a novel framework for integrating text-based and triple-based paradigms. Following Occam’s Razor, DCSK dynamically determine the necessity of structured knowledge by the designed multi-faceted evaluation, which systematically assess the correctness, clarity, and informativeness of text-based prediction. For questions that require structured knowledge, we develop an iterative fact refiner that screens for question-relevant triples, verifies their factual adequacy, and thereby effectively excludes irrelevant and redundant information. Furthermore, based on the verification, we construct an adaptive knowledge reasoner that dynamically adjusts the need for text supplementation, thus mitigating the information deficiency in selected triples. Extensive experiments on three MHQA datasets demonstrate the efficiency and effectiveness of DCSK.

Roi Cohen, Russa Biswas, Gerard de Melo

Factual completeness is a general term that captures how detailed and informative a factually correct text is. For instance, the factual sentence “Barack Obama was born in the United States” is factually correct, though less informative than the factual sentence “Barack Obama was born in Honolulu, Hawaii, United States”. Despite the known fact that LLMs tend to hallucinate and generate factually incorrect text, they might also tend to choose to generate factual text that is indeed factually correct and yet less informative than other, more informative choices. In this work, we tackle this problem by proposing an informativeness alignment mechanism. This mechanism takes advantage of recent factual informativeness benchmarks to propose an informativeness alignment objective. This objective prioritizes answers that are both correct and informative. We find that when training a model to maximize this objective or optimize its preference, we can improve not just informativeness but also factuality.