{"total":66,"rows":[{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373,"area":null},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126,"area":null},{"id":"2407.19825","title":"Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost","created":"2024-07-29","cited_by_count":109,"area":"lr"},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"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":"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":"2601.20975","title":"DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents","created":"2026-01-28","cited_by_count":50,"area":"agents"},{"id":"2310.09044","title":"KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2403.01548","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","created":"2024-03-03","cited_by_count":45,"area":null},{"id":"2401.06961","title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","created":"2024-01-13","cited_by_count":44,"area":"lr"},{"id":"2406.13805","title":"WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia","created":"2024-06-19","cited_by_count":44,"area":"rag"},{"id":"2502.05151","title":"Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation","created":"2025-02-07","cited_by_count":42,"area":"mllm"},{"id":"2402.11199","title":"Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs","created":"2024-02-17","cited_by_count":32,"area":"lr"},{"id":"2411.14258","title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","created":"2024-11-21","cited_by_count":29,"area":null},{"id":"2407.17468","title":"WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries","created":"2024-07-24","cited_by_count":26,"area":null},{"id":"2406.06950","title":"A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation","created":"2024-06-11","cited_by_count":21,"area":null},{"id":"2505.18893","title":"Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects","created":"2025-05-24","cited_by_count":19,"area":null},{"id":"2407.12843","title":"NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2512.10791","title":"The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2503.13503","title":"SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models","created":"2025-03-12","cited_by_count":15,"area":null},{"id":"2505.17126","title":"Conformal Language Model Reasoning with Coherent Factuality","created":"2025-05-21","cited_by_count":14,"area":"lr"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2410.03198","title":"PersoBench: Benchmarking Personalized Response Generation in Large Language Models","created":"2024-10-04","cited_by_count":13,"area":null},{"id":"2410.09997","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2404.00942","title":"Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs","created":"2024-04-01","cited_by_count":10,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"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":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2412.15265","title":"Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2406.09155","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2503.15990","title":"ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2310.09725","title":"KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2411.09255","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","created":"2024-11-14","cited_by_count":4,"area":null},{"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":"2502.08109","title":"HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2508.16921","title":"Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2511.03070","title":"Epidemiology of Large Language Models: A Benchmark for Observational Distribution Knowledge","created":"2025-11-04","cited_by_count":3,"area":null},{"id":"2601.04742","title":"Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval","created":"2026-01-08","cited_by_count":3,"area":"agents"},{"id":"2605.05134","title":"Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2502.18573","title":"FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models","created":"2025-02-25","cited_by_count":2,"area":"lr"},{"id":"2408.01459","title":"AgentPeerTalk: Empowering Students through Agentic-AI-Driven Discernment of Bullying and Joking in Peer Interactions in Schools","created":"2024-07-27","cited_by_count":1,"area":"agents"},{"id":"2504.03165","title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","created":"2025-04-04","cited_by_count":1,"area":"rag"},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","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":"2601.15714","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":"2602.13224","title":"A Geometric Taxonomy of Hallucinations in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2603.10765","title":"RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems","created":"2026-03-11","cited_by_count":1,"area":"rag"},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2608.03966","title":"HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification","created":"2026-08-04","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":"2504.01132","title":"Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2505.17345","title":"The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2512.07818","title":"Provable Long-Range Benefits of Next-Token Prediction","created":"2025-12-08","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":"2603.12712","title":"Design-Specification Tiling for ICL-based CAD Code Generation","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.02443","title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","created":"2026-05-04","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":"2607.27637","title":"MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.19579","title":"Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics","created":"2026-08-20","cited_by_count":0,"area":"safety"},{"id":"2609.15561","title":"Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer Perturbation","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}