小模型更会提问：面向RAG的查询澄清微调
原标题：A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation
AI 摘要
该论文提出 ClariEdge 数据集，包含约 3900 个多轮对话、检索文档及显式难负例，用于识别 RAG 场景中需要澄清的模糊查询。作者用轻量 LoRA 微调小模型，在分类准确率（96.6%）和澄清生成质量上超过多个更大模型的提示基线，且同一模型可同时用于检索前和检索后两个阶段。研究还表明难负例对区分真正模糊与看似模糊的查询至关重要。
正文节选
A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation Abstract Query clarification is essential for retrieval-augmented generation (RAG) systems that face ambiguous user queries. We consider multi-turn grounded conversational scenarios where a user query is either ill-formed or ambiguous in the context of the prior dialog or, more interestingly, it may be well-formed but when posed against retrieved documents there are multiple relevant interpretations. Th