网络安全与数据治理2025，Vol.44Issue(11)：38-44,7.DOI:10.19358/j.issn.2097-1788.2025.11.007
基于大模型上下文学习的未知意图识别方法
Intent recognition method based on in-context learning of large language models
孙颢原 1刘莹君 2于莉娜 2纪涛 2张圳锡 1吴继冰1
作者信息
- 1. 国防科技大学 大数据与决策国家级重点实验室,湖南 长沙 410073
- 2. 智能空间信息国家级重点实验室,北京 100029
- 折叠
摘要
Abstract
In the face of the complex situation of modern warfare,accurate intent recognition technology can achieve efficient un-derstanding and precise capture of commanders′ needs,thereby enhancing the accuracy and agility of military decision-making.Existing intent recognition methods typically require large amounts of manually annotated data for training,which incurs high costs and performs poorly in recognizing novel intents.To address these issues,this paper proposes an innovative solution based on large language models(LLMs)and their in-context learning capability.By leveraging the general language understanding and in-struction-following abilities of LLMs,the proposed approach can accomplish both known intent recognition and novel intent discov-ery tasks using only a small number of examples without requiring additional training,thus offering a new and efficient solution for intent recognition.关键词
大语言模型/上下文学习/提示词工程/意图识别Key words
large language model/in-context learning/prompt engineering/intent recognition分类
计算机与自动化引用本文复制引用
孙颢原,刘莹君,于莉娜,纪涛,张圳锡,吴继冰..基于大模型上下文学习的未知意图识别方法[J].网络安全与数据治理,2025,44(11):38-44,7.
