用可解释性指导查询重写，提升检索模型对模糊问题的鲁棒性。
Improving Neural Retrieval with Attribution-Guided Query Rewriting
- 基于检索器梯度计算词元重要性，作为大模型重写的软引导
- 在BEIR数据集上显著提升检索效果，尤其对隐含需求提升更大
- 适合需要处理模糊或不明确查询的智能检索系统开发者
神经检索器虽有效但脆弱：查询表述不清或存在歧义时，即使存在相关文档也可能导致排序错误。现有方法仅部分解决此问题：大语言模型（LLM）重写查询但缺乏检索器反馈；可解释性方法能识别误导性词元，但仅用于事后分析。本文提出一种基于归因的查询重写方法，利用检索器生成的词元级解释作为软引导，驱动大模型修正查询中弱化或误导性的成分，同时保留原始意图。在BEIR数据集上的评估表明，该方法持续优于强基线，尤其在隐含或模糊信息需求下表现更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。