通过归因引导的查询重写改进神经检索
Improving Neural Retrieval with Attribution-Guided Query Rewriting
AI总结：
本文提出归因引导的查询重写方法，通过标记级解释指导LLM澄清模糊查询，提升神经检索效果。
摘要：
神经检索器在效果上有效但脆弱：未充分说明或模糊的查询即使存在相关文档也可能误导排序。现有方法仅部分解决这种脆弱性：LLM在没有检索器反馈的情况下重写查询，可解释性方法识别误导性标记但仅用于事后分析。我们闭合这个循环并提出一种归因引导的查询重写方法，利用标记级解释来指导查询重写。对于每个查询，我们计算检索器的梯度基于标记归因，然后使用这些分数作为结构化提示中软指导，引导LLM澄清弱或误导性的查询组件，同时保持意图。在BEIR集合上评估，所得重写在强基线之上一致提升检索效果，对隐含或模糊的信息需求有更大的增益。
英文摘要：
Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever feedback, and explainability methods identify misleading tokens but are used for post-hoc analysis. We close this loop and propose an attribution-guided query rewriting method that uses token-level explanations to guide query rewriting. For each query, we compute gradient-based token attributions from the retriever and then use these scores as soft guidance in a structured prompt to an LLM that clarifies weak or misleading query components while preserving intent. Evaluated on BEIR collections, the resulting rewrites consistently improve retrieval effectiveness over strong baselines, with larger gains for implicit or ambiguous information needs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
