Automated Fact-Checking

Follow this topic Ask about this topic

Automated fact-checking studies how to identify verifiable claims, find relevant evidence, and judge whether claims are supported, refuted, or unresolved. Systems combine check-worthiness classifiers, web or knowledge-graph retrieval, claim decomposition, and evidence-grounded language models; newer work also handles images, video, speech, and multilingual claims. Benchmarks such as FEVER, SciFact, and AVeriTeC test retrieval and verdict quality, but results often shift across domains, languages, and evidence conditions. A central challenge is ensuring that verdicts truly follow the cited evidence while controlling retrieval errors, uncertainty, cost, and benchmark contamination.

Latest papers

139 papers17 papers in the last four weeks, up 6% on the four weeks before. 0.1% of all new papers.

Are LLMs More Skeptical of Entertainment News?
May 3, 2026Huiqian LaiFake News Detection Text Classification
School of Information Studies, Syracuse University
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
May 2, 2026Yunhan Bu, Quan Zhang, Huaping Zhang +9Structural Causal Models RL for Language Model Reasoning
Beijing Institute of Technology, Beijing, China · School of Computer Science and Technology, Xinjiang University, Urumqi, China · Military Science Information Research Center, Academy of Military Science, Beijing, China
Propagation Structure-Semantic Transfer Learning for Robust Fake News Detection
Apr 27, 2026Mengyang Chen, Lingwei Wei, Han Cao +3Fake News Detection Text Classification
Institute of Information Engineering, Chinese Academy of Sciences, Haidian District Beijing 100085, China · School of Cyber Security, University of Chinese Academy of Sciences, Huairou District Beijing 101408, China · State Key Laboratory of Communication Content Cognition, People’s Daily Online, Chaoyang District Beijing 100020, China
When Cow Urine Cures Constipation on YouTube: Limits of LLMs in Detecting Culture-specific Health Misinformation
Apr 23, 2026Anamta Khan, Ratna Kandala, Deepti +2LLM Prompting Automated Fact-Checking
University of Michigan · University of Kansas · IIT Jodhpur
Misinformation Span Detection in Videos via Audio Transcripts
Apr 23, 2026Breno Matos, Rennan C. Lima, Savvas Zannettou +2Automated Fact-Checking
Max Planck Institute for Informatics · Federal University of Minas Gerais · Kunumi Institute +1
Mask-to-Correct $^+$ : Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction
Apr 21, 2026Payel Santra, Lavisha Sharma, Madhusudan Ghosh +1Retrieval-Augmented Generation Automated Fact-Checking
Indian Association for the Cultivation of Science, Jadavpur, Kolkata-700032, India
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
Apr 21, 2026Yixuan Tang, Yirui Zhang, Hang Feng +1Multi-Agent Debate Automated Fact-Checking
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 LeeAutomated Fact-Checking
The Pennsylvania State University, USA · University of Sheffield, UK
Fact4ac at the Financial Misinformation Detection Challenge Task: Reference-Free Financial Misinformation Detection via Fine-Tuning and Few-Shot Prompting of Large Language Models
Apr 16, 2026Cuong Hoang, Le-Minh NguyenLLM Fine-Tuning Automated Fact-Checking
Japan Advanced Institute of Science and Technology
BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking
Apr 15, 2026Hyunkyung Park, Arkaitz ZubiagaAutomated Fact-Checking
Queen Mary University of London
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
Apr 15, 2026Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty +2Automated Fact-Checking Human-AI Collaboration
MBZUAI, UAE · TU Darmstadt, Germany · IIT Delhi, India
Calibrated Selective Fact-Checking via Evidence Chain Evaluation
Apr 15, 2026Dekun YangAutomated Fact-Checking Selective Prediction
Zhejiang University
TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning
Apr 14, 2026Gautama Shastry Bulusu Venkata, Santhosh Kakarla, Maheedhar Omtri Mohan +1Fake News Detection Automated Fact-Checking
George Mason University
Uncertainty-Aware Web-Conditioned Scientific Fact-Checking
Apr 13, 2026Ashwin Vinod, Katrin ErkAutomated Fact-Checking Scientific Claim Verification
University of Texas at Austin · University of Massachusetts Amherst
CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning
Apr 13, 2026Qixian Huang, Hongqiang Lin, Tong Fu +5Table QA Multimodal Reasoning
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
Apr 9, 2026Hongyi Cen, Mingxin Wang, Yule Liu +3Adversarial Text Attacks Automated Fact-Checking
Zhejiang University · The Hong Kong University of Science and Technology (Guangzhou)
What Does a Sharing Question Add? Auditing LLM Survey Scores for Misinformation
Apr 8, 2026Zonghuan Xu, Xiang Zheng, Yutao Wu +1LLM Evaluation LLM Auditing
Shanghai Key Laboratory of Multimodal Embodied AI, Shanghai, China · City University of Hong Kong, Hong Kong SAR, China · Deakin University, Australia
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM
Apr 8, 2026Bo Wang, Jing Ma, Hongzhan Lin +4Fake News Detection Automated Fact-Checking
School of Artificial Intelligence, Jilin University, China · Hong Kong Baptist University, China · Guangdong Institute of Smart Education, Jinan University, China +3
DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects
Apr 7, 2026Jason Lucas, Matt Murtagh, Ali Al-Lawati +3Fake News Detection Dialect Bias in Language Models
The Pennsylvania State University, USA · Trinity College Dublin, Ireland · MIT Lincoln Laboratory, USA
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection
Apr 6, 2026Cheng Xu, Changhong Jin, Yingjie Niu +5LLM Evaluation Fake News Detection
University College Dublin · Bebxy · Georgia Institute of Technology +1
Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity
Apr 6, 2026Jaeyoon Jung, Yejun Yoon, Kunwoo ParkAutomated Fact-Checking Vision-Language Models
School of AI Convergence, Soongsil University · MAUM AI Inc. · Department of Intelligent Semiconductors, Soongsil University
Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification
Apr 5, 2026Xinyan Ma, Xianhao Ou, Chang Li +6Knowledge Graphs Automated Fact-Checking
Harbin Institute of Technology, China · Huawei Technologies Co., Ltd., China
Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs
Apr 5, 2026Jason Chan, Robert Gaizauskas, Zhixue ZhaoAutomated Fact-Checking Neuro-Symbolic Reasoning
School of Computer Science, University of Sheffield, United Kingdom
FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification
Apr 5, 2026Ling Yue, Chaoqian Ouyang, Ruijun Huang +8Automated Peer Review Scientific Claim Verification
Rensselaer Polytechnic Institute · Sun Yat-sen University · Southeast University +1
AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
Apr 3, 2026Yuntao Du, Minh Dinh, Kaiyuan Zhang +1Claim Verification Scientific Claim Verification
Purdue University
ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models
Apr 2, 2026Delip Rao, Feijiang Han, Chris Callison-BurchClaim Verification LLM Answer Verification
University of Pennsylvania, Philadelphia, PA, USA
AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages
Apr 1, 2026Israel Abebe Azime, Jesujoba Oluwadara Alabi, Crystina Zhang +16Automated Fact-Checking Evidence Retrieval
Saarland University, Saarland Informatic Campus, Germany · Masakhane NLP · University of Waterloo, Canada +11
ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection
Mar 31, 2026Yufeng Li, Rrubaa Panchendrarajan, Arkaitz ZubiagaAutomated Fact-Checking Claim Verification
School of Electronic Engineering and Computer Science, Queen Mary University of London, London E1 4NS, U.K.
ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims
Mar 27, 2026Raia Abu Ahmad, Max Upravitelev, Aida Usmanova +2Scientific Claim Verification Automated Fact-Checking
Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI), Germany · Technische Universität Berlin, Germany · Leuphana Universität Lüneburg, Germany +1
WhatsApp Vaccine Discourse (WhaVax): An Expert-Annotated Dataset and Benchmark for Health Misinformation Detection
Mar 25, 2026Jônatas H. dos Santos, Julio C. S. Reis, Philipe Melo +9Health Misinformation Detection Fake News Detection
Universidade Federal de Minas Gerais (UFMG), Brasil · Universidade Federal de Viçosa (UFV), Brasil

May 3, 2026J/K move · Enter open · S save

Are LLMs More Skeptical of Entertainment News?

Huiqian Lai

School of Information Studies, Syracuse University

Fake News Detection Text Classification Automated Fact-Checking Language Model Bias Evaluation

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly used for automated news credibility assessment, yet it remains unclear whether they apply even-handed standards across journalistic genres. We examine whether zero-shot LLMs are more likely to misclassify legitimate entertainment news as fake than legitimate hard news, using a within-dataset design on GossipCop from FakeNewsNet. Across four frontier models, we find a clear but model-specific genre asymmetry: DeepSeek-V3.2 and GPT-5.2 show false-positive-rate gaps of 10.1 and 8.8 percentage points, respectively (both

p < .001

), whereas Claude Opus 4.6 and Gemini 3 Flash show no comparable difference. A style-swap experiment yields only limited and inconsistent changes, suggesting that the asymmetry is not reducible to stylistic register alone. Prompt-based mitigation is likewise possible but not generic: framing the model as an entertainment-news fact-checker reduces false positives for DeepSeek-V3.2 by about 50% without detectable recall loss, but offers little improvement for GPT-5.2. Exploratory qualitative coding further suggests two recurring error patterns in sampled false positives: treating private-life claims as inherently unverifiable and discounting entertainment journalism as an epistemically weaker genre. Taken together, these findings show that aggregate performance metrics can obscure structured false positives within legitimate journalism. We argue that LLM-based credibility assessment may not only evaluate truth claims but also differentially recognize the legitimacy of journalistic genres, and that evaluation should therefore include genre-stratified false-positive analysis alongside overall accuracy.