{"total":378,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810,"area":null},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339,"area":"agents"},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283,"area":"rag"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2403.04696","title":"Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification","created":"2024-03-07","cited_by_count":162,"area":null},{"id":"2305.12744","title":"Fact-Checking Complex Claims with Program-Guided Reasoning","created":"2023-05-22","cited_by_count":146,"area":"lr"},{"id":"2305.13117","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","created":"2023-05-22","cited_by_count":144,"area":null},{"id":"2305.18248","title":"Do Language Models Know When They're Hallucinating References?","created":"2023-05-29","cited_by_count":116,"area":null},{"id":"2205.12487","title":"End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models","created":"2022-05-25","cited_by_count":107,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2308.04748","title":"Fuzz4All: Universal Fuzzing with Large Language Models","created":"2023-08-09","cited_by_count":88,"area":null},{"id":"2311.09000","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","created":"2023-11-15","cited_by_count":87,"area":null},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71,"area":null},{"id":"2205.06938","title":"Generating Literal and Implied Subquestions to Fact-check Complex Claims","created":"2022-05-14","cited_by_count":66,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65,"area":"lr"},{"id":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62,"area":null},{"id":"2406.13415","title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","created":"2024-06-19","cited_by_count":61,"area":null},{"id":"2305.06590","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","created":"2023-05-11","cited_by_count":57,"area":null},{"id":"2305.16859","title":"Scientific Fact-Checking: A Survey of Resources and Approaches","created":"2023-05-26","cited_by_count":54,"area":null},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2305.13507","title":"Multimodal Automated Fact-Checking: A Survey","created":"2023-05-22","cited_by_count":53,"area":null},{"id":"2305.13186","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","created":"2023-05-22","cited_by_count":51,"area":"lr"},{"id":"2310.05177","title":"Do Large Language Models Know about Facts?","created":"2023-10-08","cited_by_count":51,"area":null},{"id":"2310.12558","title":"Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong","created":"2023-10-19","cited_by_count":51,"area":null},{"id":"2402.07401","title":"Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate","created":"2024-02-12","cited_by_count":48,"area":"agents"},{"id":"2210.13865","title":"Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation","created":"2022-10-25","cited_by_count":45,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"area":null},{"id":"2310.06498","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","created":"2023-10-10","cited_by_count":42,"area":null},{"id":"2311.09022","title":"Exploring the Potential of Large Language Models in Computational Argumentation","created":"2023-11-15","cited_by_count":42,"area":null},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2508.15804","title":"ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks","created":"2025-08-14","cited_by_count":38,"area":"agents"},{"id":"2206.11863","title":"CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking","created":"2022-06-06","cited_by_count":37,"area":null},{"id":"2309.00240","title":"FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking","created":"2023-09-01","cited_by_count":37,"area":null},{"id":"2310.05253","title":"Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models","created":"2023-10-08","cited_by_count":37,"area":"lr"},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37,"area":null},{"id":"2309.08503","title":"HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking","created":"2023-09-15","cited_by_count":35,"area":null},{"id":"2309.15337","title":"Beyond the Chat: Executable and Verifiable Text-Editing with LLMs","created":"2023-09-27","cited_by_count":35,"area":null},{"id":"2401.11969","title":"Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research","created":"2024-01-22","cited_by_count":35,"area":null},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2304.05510","title":"chatClimate: Grounding Conversational AI in Climate Science","created":"2023-04-11","cited_by_count":32,"area":null},{"id":"2305.14623","title":"Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models","created":"2023-05-24","cited_by_count":31,"area":null},{"id":"2310.13549","title":"The Perils & Promises of Fact-checking with Large Language Models","created":"2023-10-20","cited_by_count":31,"area":null},{"id":"2403.04890","title":"Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering","created":"2024-03-07","cited_by_count":31,"area":"lr"},{"id":"2204.12164","title":"CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets","created":"2022-04-26","cited_by_count":29,"area":null},{"id":"2401.08026","title":"JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims","created":"2024-01-16","cited_by_count":29,"area":null},{"id":"2402.08259","title":"A Survey of Table Reasoning with Large Language Models","created":"2024-02-13","cited_by_count":29,"area":"lr"},{"id":"2502.09083","title":"Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking","created":"2025-02-13","cited_by_count":29,"area":null},{"id":"2408.11832","title":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","created":"2024-08-06","cited_by_count":28,"area":null},{"id":"2406.07070","title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","created":"2024-06-11","cited_by_count":27,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2310.07609","title":"QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking","created":"2023-10-11","cited_by_count":26,"area":null},{"id":"2311.07453","title":"ChartCheck: Explainable Fact-Checking over Real-World Chart Images","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2308.15202","title":"Benchmarking the Generation of Fact Checking Explanations","created":"2023-08-29","cited_by_count":25,"area":null},{"id":"2305.04329","title":"FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering","created":"2023-05-07","cited_by_count":24,"area":null},{"id":"2403.07726","title":"SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2024-03-12","cited_by_count":24,"area":null},{"id":"2408.12060","title":"Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs","created":"2024-08-22","cited_by_count":24,"area":null},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24,"area":null},{"id":"2502.15844","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","created":"2025-02-20","cited_by_count":24,"area":null},{"id":"2304.03897","title":"Factify 2: A Multimodal Fake News and Satire News Dataset","created":"2023-04-08","cited_by_count":23,"area":null},{"id":"2403.17169","title":"QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims","created":"2024-03-25","cited_by_count":23,"area":null},{"id":"2308.10800","title":"Fact-checking information from large language models can decrease headline discernment","created":"2023-08-21","cited_by_count":22,"area":null},{"id":"2304.14238","title":"The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who","created":"2023-04-27","cited_by_count":19,"area":null},{"id":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19,"area":"agents"},{"id":"2407.02351","title":"Generative Large Language Models in Automated Fact-Checking: A Survey","created":"2024-07-02","cited_by_count":19,"area":null},{"id":"2502.17924","title":"FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models","created":"2025-02-25","cited_by_count":19,"area":"agents"},{"id":"2211.10057","title":"Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic","created":"2022-11-18","cited_by_count":18,"area":null},{"id":"2311.09939","title":"RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2411.05375","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2505.17978","title":"AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2305.03507","title":"Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2311.01458","title":"Detecting Deepfakes Without Seeing Any","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2410.04616","title":"Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2311.15451","title":"Uncertainty-aware Language Modeling for Selective Question Answering","created":"2023-11-26","cited_by_count":16,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2505.17762","title":"Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs","created":"2025-05-23","cited_by_count":16,"area":"rag"},{"id":"2212.01060","title":"Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning","created":"2022-12-02","cited_by_count":15,"area":null},{"id":"2401.15498","title":"Do We Need Language-Specific Fact-Checking Models? The Case of Chinese","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2406.11288","title":"MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2407.12853","title":"Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approaches","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2209.02071","title":"CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval","created":"2022-09-05","cited_by_count":14,"area":null},{"id":"2212.09683","title":"Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments","created":"2022-12-19","cited_by_count":14,"area":null},{"id":"2311.04917","title":"Adapting Fake News Detection to the Era of Large Language Models","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2402.12147","title":"Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models","created":"2024-02-19","cited_by_count":14,"area":null},{"id":"2406.03181","title":"Missci: Reconstructing Fallacies in Misrepresented Science","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2407.12943","title":"Halu-J: Critique-Based Hallucination Judge","created":"2024-07-17","cited_by_count":14,"area":null},{"id":"2503.14828","title":"The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval","created":"2025-03-19","cited_by_count":14,"area":null},{"id":"2405.05583","title":"OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2209.03755","title":"Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems","created":"2022-09-07","cited_by_count":12,"area":null},{"id":"2209.14642","title":"A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection","created":"2022-09-29","cited_by_count":12,"area":null}],"next_cursor":"100"}