Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.08772 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929311877955584 |
|---|---|
| author | Kong, Huanjun Zhang, Songyang Li, Jiaying Xiao, Min Xu, Jun Chen, Kai |
| author_facet | Kong, Huanjun Zhang, Songyang Li, Jiaying Xiao, Min Xu, Jun Chen, Kai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08772 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance Kong, Huanjun Zhang, Songyang Li, Jiaying Xiao, Min Xu, Jun Chen, Kai Computation and Language 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. |
| title | HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.08772 |