{"list":"other","total":81,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1705.00648","title":"\"Liar, Liar Pants on Fire\": A New Benchmark Dataset for Fake News Detection","created":"2017-05-01","cited_by_count":363},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"1809.01286","title":"FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media","created":"2018-09-05","cited_by_count":285},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2011.03088","title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification","created":"2020-11-05","cited_by_count":201},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167},{"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},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"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},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129},{"id":"2310.05189","title":"Factuality Challenges in the Era of Large Language Models","created":"2023-10-08","cited_by_count":126},{"id":"2104.05893","title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","created":"2021-04-13","cited_by_count":107},{"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},{"id":"2305.16339","title":"Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs","created":"2023-05-24","cited_by_count":104},{"id":"2106.03794","title":"COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic","created":"2021-06-07","cited_by_count":100},{"id":"2310.00305","title":"Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method","created":"2023-09-30","cited_by_count":97},{"id":"2106.09248","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","created":"2021-06-17","cited_by_count":91},{"id":"2104.14839","title":"The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey","created":"2021-04-30","cited_by_count":79},{"id":"2403.03170","title":"SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection","created":"2024-03-05","cited_by_count":74},{"id":"2309.12247","title":"Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection","created":"2023-09-21","cited_by_count":72},{"id":"2201.00987","title":"MDFEND: Multi-domain Fake News Detection","created":"2022-01-04","cited_by_count":68},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66},{"id":"2205.02832","title":"Entity Cloze By Date: What LMs Know About Unseen Entities","created":"2022-05-05","cited_by_count":55},{"id":"2006.04102","title":"Language Models as Fact Checkers?","created":"2020-06-07","cited_by_count":51},{"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},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50},{"id":"2411.00784","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","created":"2024-10-17","cited_by_count":39},{"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},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36},{"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},{"id":"2310.13549","title":"The Perils & Promises of Fact-checking with Large Language Models","created":"2023-10-20","cited_by_count":31},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27},{"id":"2402.05904","title":"FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs","created":"2024-02-08","cited_by_count":27},{"id":"2404.12065","title":"RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models","created":"2024-04-18","cited_by_count":27},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25},{"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},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24},{"id":"2308.10800","title":"Fact-checking information from large language models can decrease headline discernment","created":"2023-08-21","cited_by_count":22},{"id":"2310.09223","title":"Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation","created":"2023-10-13","cited_by_count":19},{"id":"2407.02351","title":"Generative Large Language Models in Automated Fact-Checking: A Survey","created":"2024-07-02","cited_by_count":19},{"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},{"id":"2311.09939","title":"RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection","created":"2023-11-16","cited_by_count":18},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18},{"id":"2502.14765","title":"Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning","created":"2025-02-20","cited_by_count":17},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15},{"id":"2309.07601","title":"Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals","created":"2023-09-14","cited_by_count":14},{"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},{"id":"2403.03627","title":"Multimodal Large Language Models to Support Real-World Fact-Checking","created":"2024-03-06","cited_by_count":13},{"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},{"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},{"id":"2405.01593","title":"Large Language Model Agent for Fake News Detection","created":"2024-04-30","cited_by_count":12},{"id":"2501.10860","title":"Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking","created":"2025-01-18","cited_by_count":12},{"id":"2406.12614","title":"EUvsDisinfo: A Dataset for Multilingual Detection of Pro-Kremlin Disinformation in News Articles","created":"2024-06-18","cited_by_count":10},{"id":"2502.16181","title":"BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking","created":"2025-02-22","cited_by_count":8},{"id":"2503.22280","title":"MultiClaimNet: A Massively Multilingual Dataset of Fact-Checked Claim Clusters","created":"2025-03-28","cited_by_count":7},{"id":"2407.11522","title":"FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models","created":"2024-07-16","cited_by_count":6},{"id":"2407.10474","title":"Multi-source Knowledge Enhanced Graph Attention Networks for Multimodal Fact Verification","created":"2024-07-15","cited_by_count":5},{"id":"2402.13244","title":"Are Fact-Checking Tools Helpful? An Exploration of the Usability of Google Fact Check","created":"2024-02-20","cited_by_count":4},{"id":"2410.12222","title":"On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation","created":"2024-10-16","cited_by_count":4},{"id":"2410.10408","title":"Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion","created":"2024-10-14","cited_by_count":3},{"id":"2411.05775","title":"Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?","created":"2024-11-08","cited_by_count":3},{"id":"2503.03417","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","created":"2025-03-05","cited_by_count":3},{"id":"2507.20700","title":"When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification","created":"2025-07-28","cited_by_count":3}],"next_cursor":null}