{"list":"other","total":226,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"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":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206},{"id":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205},{"id":"2401.15884","title":"Corrective Retrieval Augmented Generation","created":"2024-01-29","cited_by_count":197},{"id":"2502.18581","title":"Scalable Best-of-N Selection for Large Language Models via Self-Certainty","created":"2025-02-25","cited_by_count":187},{"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},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"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":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112},{"id":"2401.13835","title":"What Large Language Models Know and What People Think They Know","created":"2024-01-24","cited_by_count":110},{"id":"2311.13230","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","created":"2023-11-22","cited_by_count":99},{"id":"2503.09648","title":"A Survey on Trustworthy LLM Agents: Threats and Countermeasures","created":"2025-03-12","cited_by_count":96},{"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":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75},{"id":"2212.07769","title":"CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models","created":"2022-12-15","cited_by_count":69},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59},{"id":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55},{"id":"2405.12063","title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models","created":"2024-05-20","cited_by_count":54},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51},{"id":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46},{"id":"2510.09459","title":"Failure Prediction at Runtime for Generative Robot Policies","created":"2025-10-10","cited_by_count":42},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37},{"id":"2606.04990","title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","created":"2026-06-03","cited_by_count":37},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32},{"id":"2503.15341","title":"Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs","created":"2025-03-19","cited_by_count":32},{"id":"2502.04964","title":"Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency","created":"2025-02-07","cited_by_count":30},{"id":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29},{"id":"2305.16703","title":"Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' View","created":"2023-05-26","cited_by_count":28},{"id":"2402.10727","title":"From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation","created":"2024-02-16","cited_by_count":28},{"id":"2409.12180","title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","created":"2024-09-18","cited_by_count":26},{"id":"2505.11737","title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","created":"2025-05-16","cited_by_count":24},{"id":"2502.17214","title":"CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought","created":"2025-02-24","cited_by_count":23},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23},{"id":"2509.11575","title":"A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models","created":"2025-09-15","cited_by_count":21},{"id":"2505.13143","title":"Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models","created":"2025-05-19","cited_by_count":20},{"id":"2601.05214","title":"Internal Representations as Indicators of Hallucinations in Agent Tool Selection","created":"2026-01-08","cited_by_count":19},{"id":"2511.04418","title":"The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity","created":"2025-11-06","cited_by_count":17},{"id":"2605.01347","title":"MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate","created":"2026-05-02","cited_by_count":17},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16},{"id":"2410.10786","title":"On Information-Theoretic Measures of Predictive Uncertainty","created":"2024-10-14","cited_by_count":16},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16},{"id":"2601.06818","title":"AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents","created":"2026-01-11","cited_by_count":16},{"id":"2604.07223","title":"TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories","created":"2026-04-08","cited_by_count":16},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15},{"id":"2409.02628","title":"(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models","created":"2024-09-04","cited_by_count":15},{"id":"2502.17773","title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","created":"2025-02-25","cited_by_count":12},{"id":"2503.08308","title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","created":"2025-03-11","cited_by_count":12},{"id":"2601.02179","title":"Confidence Estimation for LLMs in Multi-turn Interactions","created":"2026-01-05","cited_by_count":12},{"id":"2606.07937","title":"Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems","created":"2026-06-06","cited_by_count":12},{"id":"2605.05583","title":"Belief Memory: Agent Memory Under Partial Observability","created":"2026-05-07","cited_by_count":11},{"id":"2509.02401","title":"Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning","created":"2025-09-02","cited_by_count":10},{"id":"2506.03723","title":"Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision","created":"2025-06-04","cited_by_count":9},{"id":"2602.21158","title":"SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards","created":"2026-02-24","cited_by_count":9},{"id":"2509.23129","title":"C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning","created":"2025-09-27","cited_by_count":8},{"id":"2602.07186","title":"The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization","created":"2026-02-06","cited_by_count":8},{"id":"2603.06604","title":"Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection","created":"2026-02-18","cited_by_count":8},{"id":"2605.03534","title":"SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation","created":"2026-05-05","cited_by_count":8},{"id":"2606.29490","title":"Reported Confidence in LLMs Tracks Commitment More Than Correctness","created":"2026-06-28","cited_by_count":8},{"id":"2507.03279","title":"Conformal Information Pursuit for Interactively Guiding Large Language Models","created":"2025-07-04","cited_by_count":7},{"id":"2601.04525","title":"GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence","created":"2026-01-08","cited_by_count":7},{"id":"2604.01413","title":"Adaptive Stopping for Multi-Turn LLM Reasoning","created":"2026-04-01","cited_by_count":7},{"id":"2604.07036","title":"ReDAct: Uncertainty-Aware Deferral for LLM Agents","created":"2026-04-08","cited_by_count":7},{"id":"2604.14799","title":"Knowing When Not to Answer: Evaluating Abstention in Multimodal Reasoning Systems","created":"2026-04-16","cited_by_count":7},{"id":"2605.18812","title":"PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines","created":"2026-05-12","cited_by_count":7},{"id":"2605.21801","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","created":"2026-05-20","cited_by_count":7},{"id":"2606.05885","title":"When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training","created":"2026-06-04","cited_by_count":7},{"id":"2606.17056","title":"The Value Axis: Language Models Encode Whether They're on the Right Track","created":"2026-06-15","cited_by_count":7},{"id":"2404.04287","title":"CONFLARE: CONFormal LArge language model REtrieval","created":"2024-04-04","cited_by_count":6}],"next_cursor":"100"}