{"total":59,"rows":[{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"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":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94,"area":null},{"id":"2403.18771","title":"CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists","created":"2024-03-27","cited_by_count":94,"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":"2305.16859","title":"Scientific Fact-Checking: A Survey of Resources and Approaches","created":"2023-05-26","cited_by_count":54,"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":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48,"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":"2305.07982","title":"Zero-shot Faithful Factual Error Correction","created":"2023-05-13","cited_by_count":26,"area":null},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"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":"2502.10855","title":"Towards Effective Extraction and Evaluation of Factual Claims","created":"2025-02-15","cited_by_count":19,"area":null},{"id":"2311.09581","title":"DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation","created":"2023-11-16","cited_by_count":16,"area":null},{"id":"2305.14341","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2410.04734","title":"TLDR: Token-Level Detective Reward Model for Large Vision Language Models","created":"2024-10-07","cited_by_count":15,"area":"mllm"},{"id":"2210.13001","title":"Modeling Information Change in Science Communication with Semantically Matched Paraphrases","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2403.17768","title":"SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2204.02007","title":"Fact Checking with Insufficient Evidence","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2402.02844","title":"Comparing Knowledge Sources for Open-Domain Scientific Claim Verification","created":"2024-02-05","cited_by_count":10,"area":null},{"id":"2206.07360","title":"SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse","created":"2022-06-15","cited_by_count":9,"area":null},{"id":"2402.14268","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2505.14599","title":"Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models","created":"2025-05-20","cited_by_count":9,"area":null},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"id":"2305.07984","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","created":"2023-05-13","cited_by_count":8,"area":null},{"id":"2310.14198","title":"QA-NatVer: Question Answering for Natural Logic-based Fact Verification","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2312.11785","title":"Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs","created":"2023-12-19","cited_by_count":8,"area":null},{"id":"2502.15419","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2505.21740","title":"Counterfactual Simulatability of LLM Explanations for Generation Tasks","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2209.07834","title":"Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweets","created":"2022-09-16","cited_by_count":7,"area":null},{"id":"2306.02569","title":"Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2402.13028","title":"Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables","created":"2024-02-20","cited_by_count":5,"area":"lr"},{"id":"2410.03341","title":"Zero-Shot Fact Verification via Natural Logic and Large Language Models","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2412.12422","title":"FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2312.10171","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2502.10003","title":"SciClaimHunt: A Large Dataset for Evidence-based Scientific Claim Verification","created":"2025-02-14","cited_by_count":4,"area":null},{"id":"2503.08890","title":"PlainQAFact: Retrieval-augmented Factual Consistency Evaluation Metric for Biomedical Plain Language Summarization","created":"2025-03-11","cited_by_count":4,"area":"rag"},{"id":"2509.16564","title":"MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2309.14966","title":"Interactively Learning Social Media Representations Improves News Source Factuality Detection","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2507.18802","title":"DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition","created":"2025-07-24","cited_by_count":3,"area":"alignment"},{"id":"2510.22055","title":"A Benchmark for Open-Domain Numerical Fact-Checking Enhanced by Claim Decomposition","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2411.15993","title":"Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2503.18526","title":"SciClaims: An End-to-End Generative System for Biomedical Claim Analysis","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2509.22101","title":"Think Right, Not More: Test-Time Scaling for Numerical Claim Verification","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2603.05308","title":"Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2408.14623","title":"MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functions","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2508.07095","title":"Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust","created":"2025-08-09","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":"2312.10700","title":"Cross-Domain Robustness of Transformer-based Keyphrase Generation","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2403.18671","title":"Fact Checking Beyond Training Set","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2405.20708","title":"FinGen: A Dataset for Argument Generation in Finance","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2410.18670","title":"Health Misinformation in Social Networks: A Survey of IT Approaches","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2512.11506","title":"EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection","created":"2025-12-12","cited_by_count":0,"area":"agents"},{"id":"2605.18776","title":"Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.20050","title":"Language Mutations Sustain the Persistences of Conspiracy Theories on Social Media","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.16212","title":"Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.03675","title":"VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.25046","title":"Peerify: Benchmarking Peer-Review Claim Verification","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}