{"list":"other","total":51,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"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":"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":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166},{"id":"2405.03553","title":"AlphaMath Almost Zero: Process Supervision without Process","created":"2024-05-06","cited_by_count":162},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136},{"id":"2504.05812","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","created":"2025-04-08","cited_by_count":128},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"2501.11120","title":"Tell me about yourself: LLMs are aware of their learned behaviors","created":"2025-01-19","cited_by_count":91},{"id":"2311.01740","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","created":"2023-11-03","cited_by_count":90},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69},{"id":"2407.00499","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","created":"2024-06-29","cited_by_count":65},{"id":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55},{"id":"2205.02318","title":"Language Models in the Loop: Incorporating Prompting into Weak Supervision","created":"2022-05-04","cited_by_count":52},{"id":"2502.11435","title":"SMART: Self-Aware Agent for Tool Overuse Mitigation","created":"2025-02-17","cited_by_count":52},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46},{"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":"2501.15602","title":"Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning","created":"2025-01-26","cited_by_count":36},{"id":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","cited_by_count":35},{"id":"2504.13367","title":"THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models","created":"2025-04-17","cited_by_count":35},{"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":"2502.13943","title":"AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence","created":"2025-02-19","cited_by_count":24},{"id":"2011.00680","title":"Modern Monte Carlo Methods for Efficient Uncertainty Quantification and Propagation: A Survey","created":"2020-11-02","cited_by_count":21},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21},{"id":"2502.14634","title":"CER: Confidence Enhanced Reasoning in LLMs","created":"2025-02-20","cited_by_count":17},{"id":"2406.10099","title":"Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning","created":"2024-06-14","cited_by_count":16},{"id":"2505.02865","title":"Accelerating Large Language Model Reasoning via Speculative Search","created":"2025-05-03","cited_by_count":16},{"id":"2505.10425","title":"Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs","created":"2025-05-15","cited_by_count":16},{"id":"2507.21931","title":"Post-Training Large Language Models via Reinforcement Learning from Self-Feedback","created":"2025-07-29","cited_by_count":15},{"id":"2412.01033","title":"SAUP: Situation Awareness Uncertainty Propagation on LLM Agent","created":"2024-12-02","cited_by_count":14},{"id":"2412.11803","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","created":"2024-12-16","cited_by_count":13},{"id":"2502.02390","title":"CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoning","created":"2025-02-04","cited_by_count":12},{"id":"2506.00780","title":"Do not Abstain! Identify and Solve the Uncertainty","created":"2025-06-01","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":"2404.14230","title":"Resistance Against Manipulative AI: key factors and possible actions","created":"2024-04-22","cited_by_count":9},{"id":"2501.12061","title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","created":"2025-01-21","cited_by_count":1}],"next_cursor":null}