{"total":22,"rows":[{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25,"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":"2502.10855","title":"Towards Effective Extraction and Evaluation of Factual Claims","created":"2025-02-15","cited_by_count":19,"area":null},{"id":"2404.12174","title":"Claim Check-Worthiness Detection: How Well do LLMs Grasp Annotation Guidelines?","created":"2024-04-18","cited_by_count":9,"area":null},{"id":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2412.14276","title":"Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2504.12325","title":"LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media","created":"2025-04-11","cited_by_count":5,"area":null},{"id":"2412.03589","title":"Human Evaluation of Procedural Knowledge Graph Extraction from Text with Large Language Models","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2506.07211","title":"Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2507.05010","title":"Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2504.09866","title":"PASS-FC: Progressive and Adaptive Search Scheme for Fact Checking of Comprehensive Claims","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2602.05692","title":"MedErrBench: A Fine-Grained Multilingual Benchmark for Medical Error Detection and Correction with Clinical Expert Annotations","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2509.15793","title":"RAVE: Retrieval and Scoring Aware Verifiable Claim Detection","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2509.15896","title":"The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2502.13628","title":"Efficient Environmental Claim Detection with Hyperbolic Graph Neural Networks","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2510.19310","title":"JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2512.06227","title":"Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2602.10017","title":"SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.16298","title":"MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.30025","title":"ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2608.27358","title":"RCMN: Understanding Misleadingness in Influential Public Discourse","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.30731","title":"Calibrating Small Language Models for Claim Check-Worthiness Detection","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}