通信学报2026，Vol.47Issue(7)：16-31,16.DOI:10.11959/j.issn.1000-436x.TXXB260132
基于大语言模型的用户目标导向小众词汇主题挖掘方法
User-targeted rare word topic mining method based on large language models
摘要
Abstract
To address challenges in niche topic word mining,including implicit slang semantics,scarce corpora for emerging terms,and significant semantic drift,the SeedLLM framework was proposed.It introduced cross-context con-sistency constraints to perform global reasoning over slang terms and capture their deep semantics.Retrieval-augmented generation was further employed to supplement external semantics for emerging words.Meanwhile,an emerging-word evaluation model and an online reinforcement learning mechanism were designed to suppress excessive retrieval and dy-namically adapt to semantic evolution.The experimental results on multiple cross-domain datasets demonstrate that the proposed method outperforms existing methods in niche topic word identification and topic aggregation,showing strong generalization and practical value.关键词
目标主题挖掘/大语言模型/强化学习/检索增强生成Key words
target topic mining/large language model/reinforcement learning/retrieval-augmented generation分类
信息技术与安全科学引用本文复制引用
曾祥,王晔,杨博捷,周斌,王志超,贾焰..基于大语言模型的用户目标导向小众词汇主题挖掘方法[J].通信学报,2026,47(7):16-31,16.基金项目
国家重点研发计划基金资助项目(No.2023YFC3306103) The National Key Research and Development Program of China(No.2023YFC3306103) （No.2023YFC3306103）
