{"total":85,"rows":[{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2406.16264","title":"One Thousand and One Pairs: A \"novel\" challenge for long-context language models","created":"2024-06-24","cited_by_count":80,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54,"area":null},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52,"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":"2509.03531","title":"Real-Time Detection of Hallucinated Entities in Long-Form Generation","created":"2025-08-26","cited_by_count":34,"area":null},{"id":"2407.10793","title":"GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework","created":"2024-07-15","cited_by_count":30,"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":"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":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"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":"2410.04616","title":"Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2505.23912","title":"LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations","created":"2025-05-29","cited_by_count":17,"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":"2410.01794","title":"Loki: An Open-Source Tool for Fact Verification","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","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":"2407.21057","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2506.04202","title":"TracLLM: A Generic Framework for Attributing Long Context LLMs","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2511.13029","title":"AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models","created":"2025-11-17","cited_by_count":13,"area":null},{"id":"2408.01419","title":"DebateQA: Evaluating Question Answering on Debatable Knowledge","created":"2024-08-02","cited_by_count":12,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2409.11798","title":"The Factuality of Large Language Models in the Legal Domain","created":"2024-09-18","cited_by_count":10,"area":null},{"id":"2411.05060","title":"A Guide to Misinformation Detection Data and Evaluation","created":"2024-11-07","cited_by_count":10,"area":null},{"id":"2412.18069","title":"Improving Factuality with Explicit Working Memory","created":"2024-12-24","cited_by_count":10,"area":null},{"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":"2602.01031","title":"HalluHard: A Hard Multi-Turn Hallucination Benchmark","created":"2026-02-01","cited_by_count":9,"area":null},{"id":"2603.23522","title":"Qworld: Question-Specific Evaluation Criteria for LLMs","created":"2026-03-06","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2506.00088","title":"HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2508.00109","title":"FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2505.18452","title":"MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2510.02330","title":"EntropyLong: Effective Long-Context Training via Predictive Uncertainty","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2604.03141","title":"Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation","created":"2026-04-03","cited_by_count":4,"area":null},{"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":"2410.10408","title":"Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2505.21786","title":"VeriTrail: Closed-Domain Hallucination Detection with Traceability","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2510.26518","title":"Human-AI Complementarity: A Goal for Amplified Oversight","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2603.00801","title":"The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents","created":"2026-02-28","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":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.15794","title":"Veracity: An Open-Source AI Fact-Checking System","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2602.02018","title":"Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.03294","title":"Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2604.07172","title":"Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2607.19322","title":"Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.17994","title":"Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees","created":"2026-08-18","cited_by_count":2,"area":null},{"id":"2406.13232","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2407.00702","title":"Scaling Technology Acceptance Analysis with Large Language Model (LLM) Annotation Systems","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2407.14371","title":"Open Artificial Knowledge","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2505.11365","title":"Phare: A Safety Probe for Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.18425","title":"Advertising in AI systems: Society must be vigilant","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2510.21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","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":"2603.01343","title":"PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.27476","title":"PeopleSearchBench: Evaluating AI-Powered People Search Platforms with Criteria-Grounded Verification","created":"2026-03-29","cited_by_count":1,"area":null},{"id":"2608.20607","title":"JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality Judge Panels to Grounded Verification","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2501.10642","title":"Iterative Tree Analysis for Medical Critics","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2512.21010","title":"LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"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":"2605.04893","title":"Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.10442","title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.20478","title":"Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.28264","title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.03628","title":"Building Reliable Long-Form Generation via Hallucination Rejection Sampling","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.09409","title":"Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.05721","title":"SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.09043","title":"Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.23640","title":"Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.28643","title":"Redesigning and Auditing Deep Research Writing for Faithful Reports","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.00492","title":"The Privacy-Hallucination Tradeoff in Differentially Private Language Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.19885","title":"Evaluating Communicative Success in Machine-Translated Conversation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.29744","title":"Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33343","title":"CHI: A Composite Hallucination Index Unifying Entity, Relation, and Quantity Dimensions for Summarization Evaluation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35028","title":"VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05547","title":"More Claims, Less Evidence: Bounded Verification of AI-Generated Digital Knowledge Artifacts","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}