{"total":24,"rows":[{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113,"area":"lr"},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86,"area":"lr"},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"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,"area":"lr"},{"id":"2501.01306","title":"Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking","created":"2025-01-02","cited_by_count":31,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2402.11452","title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","created":"2024-02-18","cited_by_count":24,"area":"lr"},{"id":"2311.16842","title":"RELIC: Investigating Large Language Model Responses using Self-Consistency","created":"2023-11-28","cited_by_count":23,"area":"lr"},{"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,"area":"lr"},{"id":"2501.10799","title":"Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback","created":"2025-01-18","cited_by_count":22,"area":"lr"},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2502.15845","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection","created":"2025-02-20","cited_by_count":18,"area":"lr"},{"id":"2410.03767","title":"Reasoning Elicitation in Language Models via Counterfactual Feedback","created":"2024-10-02","cited_by_count":14,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"id":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2505.20664","title":"Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2404.18988","title":"Markovian Transformers for Informative Language Modeling","created":"2024-04-29","cited_by_count":4,"area":"lr"},{"id":"2605.29648","title":"Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2501.05475","title":"Retrieval-Augmented Generation by Evidence Retroactivity in LLMs","created":"2025-01-07","cited_by_count":3,"area":"lr"},{"id":"2509.08721","title":"Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2502.13416","title":"Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning","created":"2025-02-19","cited_by_count":2,"area":"lr"}],"next_cursor":null}