arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.13840cs.AIcs.CL
收藏

StackRAG Agent:利用检索增强生成改进开发者问答

StackRAG Agent: Improving Developer Answers with Retrieval-Augmented Generation

University of British Columbia(不列颠哥伦比亚大学)

Davit Abrahamyan, Fatemeh H. Fard

AI总结:

针对开发者检索信息耗时、大语言模型生成答案易出现幻觉的问题,提出基于大语言模型的检索增强多智能体工具StackRAG,聚合Stack Overflow知识提升答案可靠性,初步验证效果良好。

摘要:

开发者花费大量时间查找与自身问题相关的信息。Stack Overflow一直是主流的参考资源,而随着大语言模型(LLMs)的出现,ChatGPT等生成式模型也被频繁使用。但单独使用二者都存在缺陷:检索答案耗时且繁琐,这一点从研究人员为解决该问题开发的众多工具中便可印证;另一方面,使用LLMs并不可靠,它们可能生成不相关或不可靠的答案(即幻觉)。本研究提出StackRAG——一种基于LLMs的检索增强多智能体生成工具,它结合了二者的优势:聚合来自Stack Overflow(SO)的知识,以提升生成答案的可靠性。初步评估显示,其生成的答案具备正确性、准确性、相关性与实用性。

英文摘要:

Developers spend much time finding information that is relevant to their questions. Stack Overflow has been the leading resource, and with the advent of Large Language Models (LLMs), generative models such as ChatGPT are used frequently. However, there is a catch in using each one separately. Searching for answers is time-consuming and tedious, as shown by the many tools developed by researchers to address this issue. On the other, using LLMs is not reliable, as they might produce irrelevant or unreliable answers (i.e., hallucination). In this work, we present StackRAG, a retrieval-augmented Multiagent generation tool based on LLMs that combines the two worlds: aggregating the knowledge from SO to enhance the reliability of the generated answers. Initial evaluations show that the generated answers are correct, accurate, relevant, and useful.

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。

↑