Fact-Checking

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 54

All topics

Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents
Sep 29, 2026Jianchang Su, Yiwei Yang, Wei ZhangFact-Checking AI Trustworthiness
University of Connecticut · University of California, Santa Cruz
VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
Sep 28, 2026Hanxun Huang, Yutao Wu, Qizhou Wang +9Misinformation Fact-Checking
The University of Melbourne · Deakin University · Singapore Management University +3
OpenFC: Learning Verification Policies towards Open-Search Fact Checking
Sep 27, 2026Xinming Wang, Kaixiang Qiu, Yansong Lin +5Fact-Checking
Institute of Automation, Chinese Academy of Sciences · University of Electronic Science and Technology of China · Beijing Institute of Technology +1
To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
Sep 24, 2026Debajyoti Mazumder, Mamta, Abhirama Subramanyam PenamakuriFact-Checking Misinformation
IISER Bhopal · King’s College London · MBZUAI
EnigmaForge: The Question Is Hidden in the Story
Sep 24, 2026Daniel EisnerFrontier Models Language Model Computes
R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
Sep 14, 2026Dhruv Dixit, Paritosh PandeyFact-Checking Confidence Calibration
Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken, New Jersey, United States · Department of Computer Science University of North Carolina Chapel Hill, North Carolina, United States
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
Sep 10, 2026Iliano FasolinoAgentic Retrieval-Augmented Generation Systems Large Language Model Reliability
Department of Computer Science University of Milan Milan, Italy
Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation
Sep 8, 2026Xingyu Deng, Mingzi Cao, Nikolaos Aletras +2Fact-Checking Large Language Model Reliability
University of Sheffield · Sheffield, UK
CoVer: Conflict-Aware Claim Verification
Sep 1, 2026Shuning Zhang, Dai Shi, Bohao Chu +7Fact-Checking Notes
Tsinghua University · Tongji University · University of Duisburg-Essen +5
Calibrating Small Language Models for Claim Check-Worthiness Detection
Aug 31, 2026Pratuat Amatya, V Venktesh, Vinay SettyLarge Language Model Reliability Small Large Language Models
1Factiverse AS · University of Stavanger · 3Stockholm University
ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
Aug 13, 2026Runze Zhao, Zixin Tang, Xiaoshuai Hao +4Fact-Checking Multi-Agent Reasoning
Institute of Information Engineering, Chinese Academy of Sciences · 1Zhongguancun Laboratory · 3Xiaomi EV
CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering
Aug 11, 2026Mouxiao Huang, Qiangyu Yan, Borui Jiang +1Visual Question Answering Benchmarks Captions
Huawei Technologies
Decomposition-Induced Context-Memory Conflict: When Fact-Checking Pipelines Contradict Their Own Source Text
Aug 11, 2026Yu-Feng YenFact-Checking Decomposition
Independent Researcher
Latent Fact-Checking: Detecting Misinformation through Activation Engineering
Aug 5, 2026Pedro T. Barcelos, Otávio Parraga, Marcelo M. Mussi +3Misinformation Detection Misinformation
MALTA, Machine Learning Theory and Applications Lab, PUCRS, Porto Alegre, Brazil · Kunumi Institute, Brazil
Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection
Aug 4, 2026Razieh Chalehchaleh, Reza Farahbakhsh, Noel CrespiGender Bias Fake News Detection
SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France
FACTWASH: Catching AI Rewrites That Wash Hearsay into Fact
Aug 4, 2026Alex KwonFact-Checking Facts
Independent Researcher
An Evidence-Grounded Retrieval-Augmented Transformer Framework for Health Misinformation Verification
Aug 3, 2026Isah M. Bukar, Bala Mairiga Abduljalil, Bashir Saleh Maina +1Misinformation Fact-Checking
Department of Computer Science, Yobe State University, Damaturu, Nigeria · Yobe AI Research Laboratory (YAIR Lab), Yobe State University, Damaturu, Nigeria · Center for AI & Big Data, Novosibirsk State University, Novosibirsk, Russian Federation +1
InfoOps Bench: A live information operations safety benchmark
Jul 30, 2026Dorian Quelle, Lisa-Maria Neudert, Jonathan Bright +1Artificial Intelligence Benchmarks Fact-Checking
Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking
Jul 26, 2026Haorui He, Xinwen Chen, Dacheng Wen +3Fact-Checking Reference-Guided Multimodal In-Context Verification
Department of Interactive Media, Hong Kong Baptist University · School of Computing and Data Science, The University of Hong Kong · Faculty of Science and Technology, Beijing Normal-Hong Kong Baptist University
GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning
Jul 22, 2026Zhaoqi Wang, Zijian Zhang, Xiaomei Yuan +4Fact-Checking Evidence-Grounded Questions
School of Cyberspace Science and Technology, Beijing Institute of Technology · School of Computer Science, The University of Auckland
DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration
Jul 20, 2026Cong Hoan Nguyen, Thomas Hoang, Hieu Minh Duong +1Fact-Checking Large Language Model Reliability
University of Louisville, Louisville KY 40292, USA. · Denison University, Granville, Ohio 43023, USA.
Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring
Jul 9, 2026Jennifer Za, Julija Bainiaksina, Nikita Ostrovsky +2Persuasion Chain-of-Thought Reasoning
LASR Labs · University College London · Google DeepMind
Can temporal article-level credibility signals improve domain-level credibility prediction?
Jul 6, 2026Islam Eldifrawi, Shengrui Wang, Amine TrabelsiCredibility Fact-Checking
Know Your Source: A Public Knowledge Store for Media Background Checks
Jul 2, 2026Benjamin Nichols, Michael Schlichtkrull, Nedjma OusidhoumFact-Checking Mediaref
△Cardiff University · ⋄Queen Mary University of London
Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
Jul 2, 2026Nikil Roashan Selvam, Jay Baxter, Sophie Hilgard +4Fact-Checking Crowdsourced Framework
Stanford University, Stanford, CA, USA · X Community Notes, xAI, Palo Alto, USA
How Human Feedback Shapes AI-generated Community Notes
Jun 29, 2026Soham De, Isaac Slaughter, Jiawei Guo +4Human-Ai Collaboration Content Moderation
University of Washington
ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
Jun 26, 2026Zhaoqi Wang, Zijian Zhang, Kun Zheng +4Category-Aware Atomic Claims Fact-Checking
School of Cyberspace Science and Technology, Beijing Institute of Technology · TravelSky Technology Limited · School of Computer Science, University of Auckland
Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation
Jun 24, 2026Jun Yajima, Tatsuya Oka, Takao OkuboFact-Checking Artificial Intelligence Risk
1Fujitsu Limited · Institute of Information Security
The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking
Jun 23, 2026Arka Ujjal Dey, John CollomosseFact-Checking Verdict
CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis
Jun 18, 2026Phuong Huu Vu Tran, Thuan Duc Mai, Bach Xuan LeFact-Checking Credibility
Vietnamese-German University, Ho Chi Minh City, Vietnam · Ho Chi Minh University of Technology, Ho Chi Minh City, Vietnam
A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization
Jun 14, 2026Weixiao Zhou, Gengyao Li, Xianfu Cheng +3Summarization Fact-Checking
CCSE, Beihang University · Fanyu AI Laboratory · MAIS, CASIA
From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification
Jun 11, 2026Rongxin Yang, Shenghong He, Siyuan Zhu +1Fact-Checking Reference-Guided Multimodal In-Context Verification
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Jun 3, 2026Saroj MishraAgentic Retrieval-Augmented Generation Systems Agentic Reasoning
University of North Dakota
Towards Multi-Agent-Simulation-Based Community Note Evaluation
Jun 3, 2026Changxi Wen, Shuning Zhang, Bohao Chu +5Fact-Checking Restricted Bernoulli Matrix Factorization
1Tsinghua University, Beijing, China · University of Duisburg-Essen, Duisburg, Germany · University of Luxembourg, Luxembourg +1
Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
May 31, 2026Yuxi Sun, Wenbo Shang, Wei Gao +2Fact-Checking Large Language Model Reliability
Hong Kong Baptist University · Singapore Management University
The Decision to Verify: How Warmth and User Characteristics Shape Reliance on Conversational Agents for Information Search
May 27, 2026Mert Yazan, Frederik Bungaran Ishak Situmeang, Suzan VerberneFact-Checking User Modeling
Evaluating Commercial AI Chatbots as News Intermediaries
May 21, 2026Mirac Suzgun, Emily Shen, Federico Bianchi +5Chatbots Fact-Checking
1Stanford University · 2Independent Researcher · 3Together AI.
PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political Facts
May 13, 2026Yifei ZhuPolitical Discourse Fact-Checking
The University of Hong Kong
CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction
May 12, 2026Islam Eldifrawi, Shengrui Wang, Amine TrabelsiFact-Checking Citation Hallucination Detection
RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
May 11, 2026Danni Xu, Shaojing Fan, Harry Cheng +1Fact-Checking Reference-Guided Multimodal In-Context Verification
School of Computing (SoC), National University of Singapore (NUS), Singapore · Department of Electrical and Computer Engineering (ECE), National University of Singapore (NUS), Singapore
From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence
May 7, 2026Premtim Sahitaj, Jawan Kolanowski, Ariana Sahitaj +7Fact-Checking Evidence-Grounded Questions
Technische Universität Berlin, Quality and Usability Lab, Berlin, Germany · Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI), Berlin, Germany · Harz University of Applied Sciences, Wernigerode, Germany +1
Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial
May 5, 2026Lisa C. Adams, Linus Marx, Erik Thiele Orberg +8Clinician Trust Fact-Checking
Department of Diagnostic and Interventional Radiology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany · Department of Radiation Oncology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany · Department of Internal Medicine III: Hematology and Clinical Oncology, University Hospital Regensburg, University of Regensburg, Regensburg, Germany +4
A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis
May 2, 2026Muhammad Arslan Manzoor, Dilshod Azizov, Daniil Orel +4Mediaref Fact-Checking
αMBZUAI, UAE · γUniversity of Texas at San Antonio, USA · δUniversity of Copenhagen, Denmark +1
When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis
Apr 29, 2026Juergen DietrichEpistemology Political Discourse
TRUST Project — democracy-intelligence.de
Misinformation Span Detection in Videos via Audio Transcripts
Apr 23, 2026Breno Matos, Rennan C. Lima, Savvas Zannettou +2Misinformation Fact-Checking
Max Planck Institute for Informatics · Federal University of Minas Gerais · Kunumi Institute +1
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
Apr 21, 2026Yixuan Tang, Yirui Zhang, Hang Feng +1Fact-Checking Truth
School of Computing, National University of Singapore
When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms
Apr 18, 2026Chaewan Chun, Delvin Ce Zhang, Dongwon LeeMisinformation Fact-Checking
The Pennsylvania State University, USA · University of Sheffield, UK
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
Apr 15, 2026Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty +2Fact-Checking Category-Aware Atomic Claims
MBZUAI, UAE · TU Darmstadt, Germany · IIT Delhi, India
Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification
Dec 29, 2025Svetlana Churina, Kokil Jaidka, Anab Maulana Barik +5Fact-Checking Category-Aware Atomic Claims
Centre for Trusted Internet & Community (CTIC), National University of Singapore (NUS), Singapore · Department of Communications and New Media, Centre for Trusted Internet & Community (CTIC), National University of Singapore (NUS), Singapore · School of Computing, Centre for Trusted Internet & Community (CTIC), National University of Singapore (NUS), Singapore
Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
Nov 5, 2025Shaghayegh Kolli, Richard Rosenbaum, Timo Cavelius +3Fact-Checking Category-Aware Atomic Claims
Technical University Munich
M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset
Oct 27, 2025Jiahui Geng, Jonathan Tonglet, Iryna GurevychFact-Checking Multimodal Dataset
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE · Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany · Department of Electrical Engineering, KU Leuven, Belgium +2
TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking
Oct 19, 2024Xiaocheng Zhang, Xi Wang, Yifei Lu +5Fact-Checking Explanation Consistency Score
1Harbin Institute of Technology · 2National University of Defense Technology · 3Northeastern University +3
Generative Large Language Models in Automated Fact-Checking: A Survey
Jul 2, 2024Ivan Vykopal, Matúš Pikuliak, Simon Ostermann +1Fact-Checking Large Language Model Generation
Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia · German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany +1
UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking
Date pendingSarfraz Ahmad, Hasan Iqbal, Momina Ahsan +6Urdu Multilingual Benchmark
MBZUAI

Sep 29, 2026, cs.AIJ/K move · Enter open · S save

Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents

Jianchang Su, Yiwei Yang, Wei Zhang

University of Connecticut · University of California, Santa Cruz

Fact-Checking AI Trustworthiness Large Language Model Reliability Verdict Offline Reinforcement Learning

Open paper AskPDF arXiv

Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence and its decision to search for more evidence, while the verdict should follow the evidence content. We introduce TrustSwap, a counterfactual test that swaps, lowers, or removes source labels while keeping every evidence text fixed, and measures its three output channels (the verdict, the confidence, and the search decision) separately. Across untrained and RL-trained models at two scales, three datasets, and two prompts, confidence and search respond to the labels as intended in 49 of 50 comparisons, yet a label change alone alters 4-23% of confident verdicts for Qwen3 models and up to 50% for an existing RL-trained fact-checker. Standard GRPO fine-tuning amplifies this shortcut at 8B in all six settings. To reduce it, we propose trust-swap augmentation (TSA), which trains GRPO on each claim with both its original and its label-swapped evidence under the same gold verdict. At 4B, TSA lowers the verdict flip rate by 7-35% (relative) in four of six settings, keeps accuracy and the intended confidence and search responses, outperforms reward-based alternatives in the main setting, and carries over to an unseen label-removal perturbation. An added consistency reward helps on the trained-on swap but not on unseen perturbations. At 8B, TSA's effect is not detectable, which makes scale the main open question.

Momentum

Related topics

Latest papers 54