CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 多媒体计算
Prompting Large Language Models for Automatic Question Tagging
Nuojia Xu1,2; Dizhan Xue1,2; Shengsheng Qian1,2; Quan Fang3; Jun Hu4
Source PublicationMachine Intelligence Research
2024
Pages0
Abstract

Automatic question tagging (AQT) represents a crucial task in Community Question Answering (CQA) websites. Its pivotal role lies in substantially augmenting user experience through the optimization of question-answering efficiency. Existing question tagging models focus on the features of questions and tags, ignoring the external knowledge of the real world. Large language models can work as knowledge engines for incorporating real-world facts for different tasks. However, it is difficult for large language models to output tags in the database of CQA websites. To address this challenge, we propose a Large Language Model Enhanced Question Tagging method called LLMEQT to perform the question tagging task. In LLMEQT, a traditional question tagging method is first applied to pre-retrieve tags for questions. Then prompts are formulated for LLMs to comprehend the task and select more suitable tags from the candidate tags for questions. Results of our experiments on two real-world datasets demonstrate that LLMEQT significantly enhances the automatic question tagging performance for CQA, surpassing the performance of state-of-the-art methods.

KeywordCommunity Question Answering Machine Learning Large Language Model Prompt Learning Question Tagging
Language英语
Sub direction classification数据挖掘
planning direction of the national heavy laboratory多模态协同认知
Paper associated data
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57166
Collection多模态人工智能系统全国重点实验室_多媒体计算
Corresponding AuthorShengsheng Qian
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.School of Artificial Intelligence, Beijing University of Posts and Telecommunications
4.School of Computing, National University of Singapore
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Nuojia Xu,Dizhan Xue,Shengsheng Qian,et al. Prompting Large Language Models for Automatic Question Tagging[J]. Machine Intelligence Research,2024:0.
APA Nuojia Xu,Dizhan Xue,Shengsheng Qian,Quan Fang,&Jun Hu.(2024).Prompting Large Language Models for Automatic Question Tagging.Machine Intelligence Research,0.
MLA Nuojia Xu,et al."Prompting Large Language Models for Automatic Question Tagging".Machine Intelligence Research (2024):0.
Files in This Item:
File Name/Size DocType Version Access License
mir_4.03.pdf(1493KB)期刊论文作者接受稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Nuojia Xu]'s Articles
[Dizhan Xue]'s Articles
[Shengsheng Qian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Nuojia Xu]'s Articles
[Dizhan Xue]'s Articles
[Shengsheng Qian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Nuojia Xu]'s Articles
[Dizhan Xue]'s Articles
[Shengsheng Qian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: mir_4.03.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.