{"ID":2884440,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07050","arxiv_id":"2508.07050","title":"ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability","abstract":"Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies have demonstrated that step-by-step reasoning during test-time helps improve listwise ranking performance. However, due to the scarcity of reasoning-intensive training data, existing rerankers perform poorly in many complex ranking scenarios, and the ranking ability of reasoning-intensive rerankers remains largely underdeveloped. In this paper, we first propose an automated reasoning-intensive training data synthesis framework, which sources training queries and passages from diverse domains and applies DeepSeek-R1 to generate high-quality training labels. To empower the listwise reranker with strong reasoning ability, we further propose a two-stage training approach, which includes a cold-start supervised fine-tuning (SFT) stage and a reinforcement learning (RL) stage. During the RL stage, we design a novel multi-view ranking reward tailored to the multi-turn nature of listwise ranking. Extensive experiments demonstrate that our trained reasoning-intensive reranker \\textbf{ReasonRank} outperforms existing baselines significantly and also achieves much lower latency than the pointwise reranker. Our codes are available at https://github.com/8421BCD/ReasonRank.","short_abstract":"Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies have demonstrated that step-by-step reasoning during test-time helps improve listwise ranking performance. However, due to the scarcity of r...","url_abs":"https://arxiv.org/abs/2508.07050","url_pdf":"https://arxiv.org/pdf/2508.07050v3","authors":"[\"Wenhan Liu\",\"Xinyu Ma\",\"Weiwei Sun\",\"Yutao Zhu\",\"Yuchen Li\",\"Dawei Yin\",\"Zhicheng Dou\"]","published":"2025-08-09T17:26:18Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611081,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2884440,"paper_url":"https://arxiv.org/abs/2508.07050","paper_title":"ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability","repo_url":"https://github.com/8421BCD/ReasonRank","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}