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 2407.09394cs.IR
收藏

PersonaRAG: 通过以用户为中心的代理增强检索增强生成系统

PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agents

University of Passau(帕绍大学)

Saber Zerhoudi, Michael Granitzer

AI总结:

PersonaRAG通过引入以用户为中心的代理,提升检索增强生成系统对用户需求的适应能力,实现更精准的个性化回答。

摘要:

大型语言模型(LLMs)由于知识过时和幻觉问题难以生成可靠输出。检索增强生成(RAG)模型通过引入外部知识来解决这一问题,但通常无法个性化检索过程。本文提出PersonaRAG,一种新颖的框架,通过引入以用户为中心的代理,根据实时用户数据和交互调整检索和生成。在各种问答数据集上评估表明,PersonaRAG在基准模型上表现出色,能够根据用户需求提供定制答案。结果表明,用户适应的信息检索系统具有广阔的应用前景。

英文摘要:

Large Language Models (LLMs) struggle with generating reliable outputs due to outdated knowledge and hallucinations. Retrieval-Augmented Generation (RAG) models address this by enhancing LLMs with external knowledge, but often fail to personalize the retrieval process. This paper introduces PersonaRAG, a novel framework incorporating user-centric agents to adapt retrieval and generation based on real-time user data and interactions. Evaluated across various question answering datasets, PersonaRAG demonstrates superiority over baseline models, providing tailored answers to user needs. The results suggest promising directions for user-adapted information retrieval systems.

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。

↑