{"total":20,"rows":[{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2503.06034","title":"Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning","created":"2025-03-08","cited_by_count":60,"area":"lr"},{"id":"2508.07050","title":"ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability","created":"2025-08-09","cited_by_count":42,"area":"lr"},{"id":"2411.00142","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","created":"2024-10-31","cited_by_count":34,"area":"lr"},{"id":"2310.07712","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","created":"2023-10-11","cited_by_count":31,"area":"lr"},{"id":"2505.20046","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2508.16998","title":"DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation","created":"2025-08-23","cited_by_count":11,"area":"lr"},{"id":"2512.00968","title":"Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search","created":"2025-11-30","cited_by_count":11,"area":"lr"},{"id":"2405.13131","title":"Atomic Self-Consistency for Better Long Form Generations","created":"2024-05-21","cited_by_count":10,"area":"lr"},{"id":"2311.08390","title":"Predicting Text Preference Via Structured Comparative Reasoning","created":"2023-11-14","cited_by_count":6,"area":"lr"},{"id":"2505.18601","title":"Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2509.07163","title":"Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval","created":"2025-09-08","cited_by_count":5,"area":"lr"},{"id":"2510.13217","title":"LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2505.23982","title":"MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2506.21638","title":"R1-Ranker: Teaching LLM Rankers to Reason","created":"2025-06-25","cited_by_count":1,"area":"lr"},{"id":"2601.09151","title":"Interpretable Probability Estimation with LLMs via Shapley Reconstruction","created":"2026-01-14","cited_by_count":1,"area":"lr"},{"id":"2602.21756","title":"Offline Reasoning for Efficient Recommendation: LLM-Empowered Persona-Profiled Item Indexing","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2412.14405","title":"RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs","created":"2024-12-18","cited_by_count":0,"area":"lr"},{"id":"2604.08834","title":"BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2604.15621","title":"Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking","created":"2026-04-17","cited_by_count":0,"area":"lr"}],"next_cursor":null}