Ask-EDA：一款由 LLM、混合 RAG 和缩写去幻觉赋能的设计助手
Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucination
AI总结：
本文提出 Ask-EDA 设计助手，融合 LLM、混合 RAG 与 ADH，并通过三个专用数据集验证其在问答、命令处理和缩写解析上的显著效果。
摘要：
电子设计工程师在设计构建、验证和技术开发过程中，面临着为大量任务高效查找相关信息的挑战。大型语言模型（LLM）有潜力通过充当可有效发挥领域专家作用的对话代理来帮助提高生产力。本文展示了 Ask-EDA，这一聊天代理旨在成为全天候可用的专家，为设计工程师提供指导。Ask-EDA 利用 LLM、混合检索增强生成（RAG）和缩写去幻觉（ADH）技术，提供更相关、更准确的回答。我们构建了三个评估数据集，即 q2a-100、cmds-100 和 abbr-100。每个数据集都针对评估不同方面而定制：通用设计问答、设计命令处理和缩写解析。我们证明，与不使用 RAG 相比，混合 RAG 在 q2a-100 数据集上的召回率提升超过 40%，在 cmds-100 数据集上提升超过 60%，而 ADH 在 abbr-100 数据集上使召回率提升超过 70%。评估结果表明，Ask-EDA 能够有效回应与设计相关的查询。
英文摘要：
Electronic design engineers are challenged to find relevant information efficiently for a myriad of tasks within design construction, verification and technology development. Large language models (LLM) have the potential to help improve productivity by serving as conversational agents that effectively function as subject-matter experts. In this paper we demonstrate Ask-EDA, a chat agent designed to serve as a 24x7 expert available to provide guidance to design engineers. Ask-EDA leverages LLM, hybrid retrieval augmented generation (RAG) and abbreviation de-hallucination (ADH) techniques to deliver more relevant and accurate responses. We curated three evaluation datasets, namely q2a-100, cmds-100 and abbr-100. Each dataset is tailored to assess a distinct aspect: general design question answering, design command handling and abbreviation resolution. We demonstrated that hybrid RAG offers over a 40% improvement in Recall on the q2a-100 dataset and over a 60% improvement on the cmds-100 dataset compared to not using RAG, while ADH yields over a 70% enhancement in Recall on the abbr-100 dataset. The evaluation results show that Ask-EDA can effectively respond to design-related inquiries.
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。
