arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.08772cs.CL
收藏

HuixiangDou:基于大语言模型的技术助力攻克群聊场景难题

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Shanghai AI Laboratory(上海人工智能实验室)

Huanjun Kong, Songyang Zhang, Jiaying Li, Min Xiao, Jun Xu, Kai Chen

AI总结:

本研究提出LLM驱动的技术助手HuixiangDou,适配IM群聊场景,可解答开源算法技术问题且不刷屏,明确了技术助手类LLM的三项核心要求,并开源了相关代码与应用。

摘要:

本研究提出了HuixiangDou——一款由大语言模型(Large Language Models, LLM)驱动的技术助手。该系统旨在为算法开发者提供支持,针对开源算法项目(如OpenMMLab旗下的计算机视觉、深度学习项目)相关问题给出有深度的解答。我们进一步探索了将该助手集成到微信、飞书等即时通讯(IM)工具的群聊中的方案。经过多轮迭代优化与试验,我们打造出一款成熟的技术聊天助手,既能有效解答用户的技术问题,又不会造成消息刷屏。本文的贡献包括:1)设计了一套专门适配群聊场景的算法流水线;2)验证了text2vec在任务拒识(即弃权(不执行)无关任务)中的可靠性能;3)明确了大语言模型在技术助手类产品中的三项核心要求,分别是打分能力、上下文学习(In-Context Learning, ICL)以及长上下文能力。我们已在GitHub(https://github.com/internlm/huixiangdou)、OpenXLab(https://openxlab.org.cn/apps/detail/tpoisonooo/huixiangdou-web)和YouTube(https://youtu.be/ylXrT-Tei-Y)开放了源代码、安卓应用与网页服务,以支撑后续研究与应用。HuixiangDou可适配即时通讯工具中的任意群聊场景。

英文摘要:

In this work, we present HuixiangDou, a technical assistant powered by Large Language Models (LLM). This system is designed to assist algorithm developers by providing insightful responses to questions related to open-source algorithm projects, such as computer vision and deep learning projects from OpenMMLab. We further explore the integration of this assistant into the group chats of instant messaging (IM) tools such as WeChat and Lark. Through several iterative improvements and trials, we have developed a sophisticated technical chat assistant capable of effectively answering users' technical questions without causing message flooding. This paper's contributions include: 1) Designing an algorithm pipeline specifically for group chat scenarios; 2) Verifying the reliable performance of text2vec in task rejection; 3) Identifying three critical requirements for LLMs in technical-assistant-like products, namely scoring ability, In-Context Learning (ICL), and Long Context. We have made the source code, android app and web service available at Github (https://github.com/internlm/huixiangdou), OpenXLab (https://openxlab.org.cn/apps/detail/tpoisonooo/huixiangdou-web) and YouTube (https://youtu.be/ylXrT-Tei-Y) to aid in future research and application. HuixiangDou is applicable to any group chat within IM tools.

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。

↑