{"list":"other","total":72,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150},{"id":"2308.16175","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","created":"2023-08-30","cited_by_count":122},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62},{"id":"2403.02509","title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","created":"2024-03-04","cited_by_count":56},{"id":"2404.02655","title":"Calibrating the Confidence of Large Language Models by Eliciting Fidelity","created":"2024-04-03","cited_by_count":47},{"id":"2506.17419","title":"UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making","created":"2025-06-20","cited_by_count":42},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41},{"id":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38},{"id":"2405.02079","title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","created":"2024-05-03","cited_by_count":36},{"id":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32},{"id":"2507.16488","title":"ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs","created":"2025-07-22","cited_by_count":32},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30},{"id":"2506.00245","title":"Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity","created":"2025-05-30","cited_by_count":28},{"id":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26},{"id":"2502.17026","title":"Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology","created":"2025-02-24","cited_by_count":25},{"id":"2502.11021","title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","created":"2025-02-16","cited_by_count":21},{"id":"2503.02863","title":"SteerConf: Steering LLMs for Confidence Elicitation","created":"2025-03-04","cited_by_count":20},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20},{"id":"2502.15845","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection","created":"2025-02-20","cited_by_count":18},{"id":"2502.16820","title":"Uncertainty Quantification of Large Language Models through Multi-Dimensional Responses","created":"2025-02-24","cited_by_count":18},{"id":"2504.19254","title":"Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers","created":"2025-04-27","cited_by_count":18},{"id":"2601.19921","title":"Demystifying Multi-Agent Debate: The Role of Confidence and Diversity","created":"2026-01-09","cited_by_count":18},{"id":"2506.01114","title":"Reconsidering LLM Uncertainty Estimation Methods in the Wild","created":"2025-06-01","cited_by_count":17},{"id":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16},{"id":"2505.24778","title":"Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?","created":"2025-05-30","cited_by_count":16},{"id":"2503.05980","title":"SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs","created":"2025-03-07","cited_by_count":14},{"id":"2506.04832","title":"Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models","created":"2025-06-05","cited_by_count":14},{"id":"2509.25532","title":"Calibrating Verbalized Confidence with Self-Generated Distractors","created":"2025-09-29","cited_by_count":14},{"id":"2406.19712","title":"Uncertainty Quantification in Large Language Models Through Convex Hull Analysis","created":"2024-06-28","cited_by_count":13},{"id":"2601.02179","title":"Confidence Estimation for LLMs in Multi-turn Interactions","created":"2026-01-05","cited_by_count":12},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10},{"id":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8},{"id":"2602.24195","title":"Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume","created":"2026-02-27","cited_by_count":8},{"id":"2406.12784","title":"UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions","created":"2024-06-18","cited_by_count":7},{"id":"2506.09684","title":"Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models","created":"2025-06-11","cited_by_count":6},{"id":"2507.07236","title":"Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification","created":"2025-07-09","cited_by_count":6},{"id":"2409.18968","title":"Safety challenges of AI in medicine in the era of large language models","created":"2024-09-11","cited_by_count":5},{"id":"2506.07575","title":"Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models","created":"2025-06-09","cited_by_count":5},{"id":"2506.07309","title":"ConfRAG: Confidence-Guided Retrieval-Augmenting Generation","created":"2025-06-08","cited_by_count":4},{"id":"2509.07925","title":"GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models","created":"2025-09-09","cited_by_count":3},{"id":"2509.12908","title":"All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning","created":"2025-09-16","cited_by_count":3},{"id":"2603.24967","title":"The Anatomy of Uncertainty in LLMs","created":"2026-03-26","cited_by_count":2}],"next_cursor":null}