QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage Reranking

  • 类型:arxiv
  • 标识:2609.30904
  • 链接:http://arxiv.org/abs/2609.30904v1
  • 主分类:rag
  • 形态:method
  • TLDR:Passage reranking plays a crucial role in information retrieval by refining the ordering of candidate passages to better reflect relevance. Existing listwise LLM rerankers with Chain-of-Thought (CoT) reasoning can handle complex queries effectively, but they suffer from substantial redundancy and high latency due to sliding-window strategies, which repeatedly generate highly similar CoTs. To address this, we propose QReason, a decoupled framework that separates query-focused reasoning from window-specific passage relevance assessment. Specifically, QReason introduces a dedicated rewriter that
  • 待LLM分类:否
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-29-rag-retrieval-reranking-candidates.json