基于语料反馈的多步查询重写用于对话搜索
原标题：Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search
AI 摘要
该论文将对话式查询重写（CQR）重新定义为序列检索问题：智能体先重写当前轮次、检索，再根据返回段落条件化下一次重写。智能体在三种类型化重写操作（意图解析、词汇改写、合成伪文档）及停止动作间选择，仅用检索质量作为奖励，通过监督微调加强化学习训练，无需人工重写标注。在TopiOCQA和QReCC上优于多个检索对齐基线，跨检索后端有效，并零样本泛化到CAsT基准。
正文节选
Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search Abstract Conversational Query Rewriting (CQR) turns a context dependent user turn into a standalone query for a retriever, and most methods do this in a single step from the dialogue history before retrieving once. The rewrite is therefore fixed before any corpus evidence is available to correct its reference resolution or its vocabulary. We recast CQR as a sequential retrieval problem: an agent rewrites the curren