大模型小模型协作，持续识别新型假新闻
Lifelong Evolution: Collaborative Learning between Large and Small Language Models for Continuous Emergent Fake News Detection
- 大模型提供泛化能力，小模型专注分类精准度，双模型多轮协同学习
- 在Pheme和Twitter16数据集上，准确率显著提升，适应假新闻动态演化
- 支持知识持续更新与旧知识保留，适合长期在线监测场景
社交媒体上假新闻的广泛传播已对社会造成严重影响。传统小语言模型（SLMs）依赖大量标注数据，难以应对新闻环境变化；大语言模型（LLMs）虽具备零样本能力，但因知识过时且缺乏合适示例，检测效果不佳。本文提出一种连续协同涌现假新闻检测框架C$^2$EFND，通过多轮协同学习结合LLMs的泛化能力与SLMs的分类专长。引入基于专家混合（Mixture-of-Experts）的终身知识编辑模块，实现对LLMs的增量更新，并采用基于回放的持续学习方法，使SLMs无需完全重训即可保留历史知识。在Pheme和Twitter16数据集上的实验表明，该框架显著优于现有方法，在持续演化的假新闻场景中有效提升检测准确率与适应性。
原文摘要 · Abstract (English)
The widespread dissemination of fake news on social media has significantly impacted society, resulting in serious consequences. Conventional deep learning methodologies employing small language models (SLMs) suffer from extensive supervised training requirements and difficulties adapting to evolving news environments due to data scarcity and distribution shifts. Large language models (LLMs), despite robust zero-shot capabilities, fall short in accurately detecting fake news owing to outdated knowledge and the absence of suitable demonstrations. In this paper, we propose a novel Continuous Collaborative Emergent Fake News Detection (C$^2$EFND) framework to address these challenges. The C$^2$EFND framework strategically leverages both LLMs' generalization power and SLMs' classification expertise via a multi-round collaborative learning framework. We further introduce a lifelong knowledge editing module based on a Mixture-of-Experts architecture to incrementally update LLMs and a replay-based continue learning method to ensure SLMs retain prior knowledge without retraining entirely. Extensive experiments on Pheme and Twitter16 datasets demonstrate that C$^2$EFND significantly outperforms existed methods, effectively improving detection accuracy and adaptability in continuous emergent fake news scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。