从文本块到功能证据：面向EDA文档问答的功能感知检索
原标题：From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA
AI 摘要
浙江大学与上海创新研究院的研究者提出面向EDA文档问答的「功能感知检索」方法，将RAG的检索单元从孤立文本块改为由类型化工件组成的EDA功能单元，并以超边记录其成员关系与来源。该方法训练编码器对齐查询与功能单元，结合单元检索与直接块检索，再由统一重排器选择证据。在新构建的EDADocEval-QA数据集上ROUGE-L较Chunk RAG提升37.1%、较最强图基线提升55.6%，在公开ORD-MMBench上提升30.0%。
正文节选
From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA Abstract Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not model reasoning but a mismatch between a query and the way knowledge is organized for retrieval. This mismatch is pronounced in Electronic Design Automation (EDA) documentation, where the information needed for an answer is scattered acros