arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.16631cs.CLcs.CYcs.SI
收藏

让沉默发声:利用大语言模型生成的评论增强假新闻检测

Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)

Qiong Nan, Qiang Sheng, Juan Cao, Beizhe Hu, Danding Wang, Jintao Li

AI总结:

针对评论不足导致假新闻检测不完整的问题,提出利用大语言模型模拟用户生成多样化评论的GenFEND框架,实验证明其有效且生成评论优于真实评论。

摘要:

假新闻检测在保护社交媒体用户和维护健康的新闻生态系统中发挥着至关重要的作用。在现有研究中,基于评论的假新闻检测方法在经验上被证明是有前景的,因为评论能够反映用户的观点、立场和情感,并加深模型对假新闻的理解。然而,由于曝光偏差和用户评论意愿的不同,在现实中获取多样化的评论并不容易,尤其是在早期检测场景中。如果无法获得“沉默”用户的评论,感知到的观点可能不完整,从而影响新闻真实性的判断。在本文中,我们探索寻找替代评论来源的可能性,以保证多样化评论的可用性,特别是来自沉默用户的评论。具体而言,我们提出采用大语言模型(LLMs)作为用户模拟器和评论生成器,并设计了GenFEND,一种生成反馈增强的检测框架,该框架通过使用多样化用户画像提示LLMs生成评论,并聚合来自多个子人群组的生成评论。实验证明了GenFEND的有效性,进一步分析表明,生成的评论覆盖了更多样化的用户,甚至可能比真实评论更有效。

英文摘要:

Fake news detection plays a crucial role in protecting social media users and maintaining a healthy news ecosystem. Among existing works, comment-based fake news detection methods are empirically shown as promising because comments could reflect users' opinions, stances, and emotions and deepen models' understanding of fake news. Unfortunately, due to exposure bias and users' different willingness to comment, it is not easy to obtain diverse comments in reality, especially for early detection scenarios. Without obtaining the comments from the ``silent'' users, the perceived opinions may be incomplete, subsequently affecting news veracity judgment. In this paper, we explore the possibility of finding an alternative source of comments to guarantee the availability of diverse comments, especially those from silent users. Specifically, we propose to adopt large language models (LLMs) as a user simulator and comment generator, and design GenFEND, a generated feedback-enhanced detection framework, which generates comments by prompting LLMs with diverse user profiles and aggregating generated comments from multiple subpopulation groups. Experiments demonstrate the effectiveness of GenFEND and further analysis shows that the generated comments cover more diverse users and could even be more effective than actual comments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑