Treffer: 基于大模型上下文学习的未知意图识别方法.

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 navel 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 LM, 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. [ABSTRACT FROM AUTHOR]

面对现代化战争的复杂态势, 精准的意图识别技术可实现对指挥人员需求的高效理解与精准捕捉, 提升决策准确率和敏捷性。现有意图识别方法通常需要大量人工标注的数据进行训练, 带来了高昂的成本, 并且对于新意图的识别效果较差。为此, 提出了基于大语言模型 (Large Language Models, LLMs) 上下文学习的创新解决办法, 充分利用大模型的通用语言能力和指令遵循能力, 仅需使用少量样本并无需训练, 便可完成已知意图识别与新意图发现任务, 为意图识别提供了一种新型高效的解决方案。 [ABSTRACT FROM AUTHOR]

Copyright of Cyber Security & Data Governance is the property of Editorial Office of Information Technology & Network Security and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)