{"total":87,"rows":[{"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":"2503.22458","title":"Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey","created":"2025-03-28","cited_by_count":57,"area":"agents"},{"id":"2406.20079","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","created":"2024-06-28","cited_by_count":44,"area":null},{"id":"2412.10510","title":"DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts","created":"2024-12-13","cited_by_count":43,"area":null},{"id":"2411.00784","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","created":"2024-10-17","cited_by_count":39,"area":null},{"id":"2402.11943","title":"LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation","created":"2024-02-19","cited_by_count":28,"area":null},{"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":"2406.11278","title":"Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs","created":"2024-06-17","cited_by_count":23,"area":null},{"id":"2412.13175","title":"DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation","created":"2024-12-17","cited_by_count":22,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2403.01152","title":"A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization","created":"2024-03-02","cited_by_count":19,"area":null},{"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":"2502.10855","title":"Towards Effective Extraction and Evaluation of Factual Claims","created":"2025-02-15","cited_by_count":19,"area":null},{"id":"2410.01794","title":"Loki: An Open-Source Tool for Fact Verification","created":"2024-10-02","cited_by_count":16,"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":"2411.05980","title":"FactLens: Benchmarking Fine-Grained Fact Verification","created":"2024-11-08","cited_by_count":10,"area":null},{"id":"2412.20251","title":"ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty","created":"2024-12-28","cited_by_count":10,"area":null},{"id":"2503.15354","title":"Optimizing Decomposition for Optimal Claim Verification","created":"2025-03-19","cited_by_count":10,"area":null},{"id":"2603.05912","title":"DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality","created":"2026-03-06","cited_by_count":10,"area":"agents"},{"id":"2412.17031","title":"A Reality Check on Context Utilisation for Retrieval-Augmented Generation","created":"2024-12-22","cited_by_count":9,"area":"rag"},{"id":"2506.12538","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2507.17015","title":"Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2511.09008","title":"A Neurosymbolic Approach to Natural Language Formalization and Verification","created":"2025-11-12","cited_by_count":9,"area":null},{"id":"2502.16181","title":"BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking","created":"2025-02-22","cited_by_count":8,"area":null},{"id":"2505.16973","title":"VeriFastScore: Speeding up long-form factuality evaluation","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.12839","title":"FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2404.06742","title":"Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking","created":"2024-04-10","cited_by_count":7,"area":null},{"id":"2503.05565","title":"Evaluating open-source Large Language Models for automated fact-checking","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2505.12348","title":"Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification","created":"2025-05-18","cited_by_count":6,"area":"lr"},{"id":"2505.21072","title":"Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation","created":"2025-05-27","cited_by_count":6,"area":"rag"},{"id":"2506.20844","title":"The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers","created":"2025-06-25","cited_by_count":6,"area":null},{"id":"2509.17436","title":"MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses","created":"2025-09-22","cited_by_count":6,"area":null},{"id":"2505.15063","title":"UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking","created":"2025-05-21","cited_by_count":4,"area":"agents"},{"id":"2510.22967","title":"MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs","created":"2025-10-27","cited_by_count":4,"area":"agents"},{"id":"2604.23588","title":"FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification","created":"2026-04-26","cited_by_count":4,"area":null},{"id":"2402.14293","title":"Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2411.05762","title":"Multi-hop Evidence Pursuit Meets the Web: Team Papelo at FEVER 2024","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2503.03703","title":"SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2505.16576","title":"EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human Actions","created":"2025-05-22","cited_by_count":3,"area":"agents"},{"id":"2506.12552","title":"Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts","created":"2025-06-14","cited_by_count":3,"area":null},{"id":"2506.19607","title":"Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2501.18265","title":"Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2503.18293","title":"Fact-checking AI-generated news reports: Can LLMs catch their own lies?","created":"2025-03-24","cited_by_count":2,"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":"2510.00880","title":"HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation","created":"2025-10-01","cited_by_count":2,"area":"lr"},{"id":"2510.06823","title":"Exposing Citation Vulnerabilities in Generative Engines","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2511.07689","title":"Stress Testing Factual Consistency Metrics for Long-Document Summarization","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2512.21635","title":"Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2505.15050","title":"Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.17855","title":"Explaining Sources of Uncertainty in Automated Fact-Checking","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2510.27238","title":"DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2601.06666","title":"InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2601.11293","title":"One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2602.11106","title":"TEGRA: Text Encoding With Graph and Retrieval Augmentation for Misinformation Detection","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.09654","title":"Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.13706","title":"Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models","created":"2026-04-15","cited_by_count":1,"area":"lr"},{"id":"2606.08605","title":"Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2401.01717","title":"Fact-checking based fake news detection: a review","created":"2024-01-03","cited_by_count":0,"area":null},{"id":"2408.04114","title":"Zero-shot Factual Consistency Evaluation Across Domains","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2408.16264","title":"LoraMap: Harnessing the Power of LoRA Connections","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2410.17112","title":"Enhancing Answer Attribution for Faithful Text Generation with Large Language Models","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2506.03051","title":"Facts Do Care About Your Language: Assessing Answer Quality of Multilingual LLMs","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2510.13749","title":"Assessing Web Search Credibility and Response Groundedness in Chat Assistants","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.05501","title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.22858","title":"RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms","created":"2025-11-28","cited_by_count":0,"area":"rag"},{"id":"2601.02574","title":"Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.04857","title":"MisSpans: Fine-Grained False Span Identification in Cross-Domain Fake News","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.22361","title":"MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.10380","title":"The Alignment Bottleneck in Decomposition-Based Claim Verification","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.01657","title":"What Do Claim Verification Datasets Actually Test? A Reasoning Trace Analysis","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2605.03971","title":"Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.29712","title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","created":"2026-05-28","cited_by_count":0,"area":"rag"},{"id":"2605.31136","title":"Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.18268","title":"Towards Multi-Agent-Simulation-Based Community Note Evaluation","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.10402","title":"Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.00205","title":"Averaging Bias: Human Faithfulness Annotations are not Locally Faithful","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.05228","title":"TriQua: Reconciling Granularity and Context in Factuality Evaluation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.23390","title":"Cross-lingual Biography Enrichment via Claim Extraction and Alignment","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.23811","title":"Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Search","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.26118","title":"ElementCheck: Complexity-Aware Long-Form Text Factuality Evaluation via Sentence Elements","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.00508","title":"CoVer: Conflict-Aware Claim Verification","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.00581","title":"Enoki: Efficient Multi-Level Hallucination Detection","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.35461","title":"AraDynFact: Dynamic Evaluation of Factual Knowledge in Arabic","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16141","title":"Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}