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 2409.04593cs.CL
收藏

Paper Copilot:用于强化学术辅助的自进化高效 LLM 系统

Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Carnegie Mellon University(卡内基梅隆大学);Carleton College(卡尔顿学院)

Guanyu Lin, Tao Feng, Pengrui Han, Ge Liu, Jiaxuan You

AI总结:

针对科研文献过载与现有文档问答缺乏个性化、实时性的问题,本文提出基于思维检索、用户画像和高性能优化的自进化 LLM 系统 Paper Copilot,可提供个性化服务并节省 69.92% 的时间。

摘要:

随着科学研究的激增,研究人员面临着浏览和阅读大量文献这一艰巨任务。现有解决方案(如文档问答)无法高效地提供个性化且最新的信息。我们提出了 Paper Copilot,这是一个自进化、高效的 LLM 系统,旨在基于思维检索、用户画像和高性能优化来帮助研究人员。具体而言,Paper Copilot 能够提供个性化研究服务,并维护一个实时更新的数据库。定量评估表明,在高效部署后,Paper Copilot 节省了 69.92% 的时间。本文详细介绍了 Paper Copilot 的设计与实现,重点阐述了其对强化学术支持的贡献,以及简化研究流程的潜力。

英文摘要:

As scientific research proliferates, researchers face the daunting task of navigating and reading vast amounts of literature. Existing solutions, such as document QA, fail to provide personalized and up-to-date information efficiently. We present Paper Copilot, a self-evolving, efficient LLM system designed to assist researchers, based on thought-retrieval, user profile and high performance optimization. Specifically, Paper Copilot can offer personalized research services, maintaining a real-time updated database. Quantitative evaluation demonstrates that Paper Copilot saves 69.92\% of time after efficient deployment. This paper details the design and implementation of Paper Copilot, highlighting its contributions to personalized academic support and its potential to streamline the research process.

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。

↑