{"total":65,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"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,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50,"area":null},{"id":"2509.00496","title":"ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics","created":"2025-08-30","cited_by_count":49,"area":null},{"id":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48,"area":null},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"id":"2409.16191","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","created":"2024-09-24","cited_by_count":44,"area":null},{"id":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"area":null},{"id":"2309.08503","title":"HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking","created":"2023-09-15","cited_by_count":35,"area":null},{"id":"2402.17124","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","created":"2024-02-27","cited_by_count":27,"area":null},{"id":"2402.15089","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","created":"2024-02-23","cited_by_count":26,"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":"2402.02008","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","created":"2024-02-03","cited_by_count":21,"area":null},{"id":"2410.16708","title":"Atomic Fact Decomposition Helps Attributed Question Answering","created":"2024-10-22","cited_by_count":21,"area":null},{"id":"2507.01001","title":"SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks","created":"2025-07-01","cited_by_count":20,"area":null},{"id":"2506.01829","title":"CiteEval: Principle-Driven Citation Evaluation for Source Attribution","created":"2025-06-02","cited_by_count":19,"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":"2412.14556","title":"CitaLaw: Enhancing LLM with Citations in Legal Domain","created":"2024-12-19","cited_by_count":16,"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":"2411.07237","title":"Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries","created":"2024-11-11","cited_by_count":12,"area":null},{"id":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2504.15219","title":"EvalAgent: Discovering Implicit Evaluation Criteria from the Web","created":"2025-04-21","cited_by_count":11,"area":null},{"id":"2310.02778","title":"Integrating UMLS Knowledge into Large Language Models for Medical Question Answering","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2508.17670","title":"CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2405.05938","title":"DOLOMITES: Domain-Specific Long-Form Methodical Tasks","created":"2024-05-09","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":"2508.15396","title":"Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2404.15894","title":"Assessing The Potential Of Mid-Sized Language Models For Clinical QA","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2311.16588","title":"Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2410.03726","title":"Neurosymbolic AI approach to Attribution in Large Language Models","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2409.13902","title":"Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2602.21045","title":"PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2603.12249","title":"SciMDR: Advancing Scientific Multimodal Document Reasoning","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2402.18589","title":"Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2411.02448","title":"Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2510.21118","title":"The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection","created":"2025-10-24","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":"2601.15714","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":"2602.01285","title":"Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2602.21059","title":"An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.16686","title":"No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.10328","title":"ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2607.24236","title":"CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2408.04114","title":"Zero-shot Factual Consistency Evaluation Across Domains","created":"2024-08-07","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":"2506.21567","title":"BioPars: A Pretrained Biomedical Large Language Model for Persian Biomedical Text Mining","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2508.08942","title":"Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.15085","title":"LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2602.19158","title":"DoAtlas-1: A Causal Compilation Paradigm for Clinical AI","created":"2026-02-22","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":"2606.22807","title":"Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.27047","title":"NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.19981","title":"HealMed: Multilingual Evaluation of Large Language Models in Medicine","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.23507","title":"When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.20574","title":"DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.39229","title":"RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15208","title":"PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}