用大模型生成个性化辟谣内容，提升用户识别假消息能力
MisinfoEval: Generative AI in the Era of "Alternative Facts"
- 设计可大规模生成辟谣内容的框架，结合模拟社交环境测试效果
- 个性化干预使用户判断准确率最高提升41.72%，显著优于通用信息
- 适合关注虚假信息治理、个性化传播策略的研究者与平台方
社交媒体上的虚假信息传播威胁民主进程，造成巨大经济损失并危害公共健康。现有应对方法多基于知识匮乏模型，通过提供事实来提升用户批判性思维，但受限于可扩展性及用户认知偏见。生成式AI为跨意识形态规模干预提供了新可能。本文提出MisinfoEval框架，用于生成和全面评估基于大语言模型（LLM）的虚假信息干预措施。实验一在模拟社交环境中评估干预有效性；实验二针对用户人口统计特征与既有信念定制个性化解释，以价值观共鸣方式对抗虚假信息。结果表明，基于LLM的干预能显著纠正用户行为，整体可靠性标注准确率最高提升41.72%。个性化干预更受用户青睐，且显著提高其识别虚假信息的能力。
原文摘要 · Abstract (English)
The spread of misinformation on social media platforms threatens democratic processes, contributes to massive economic losses, and endangers public health. Many efforts to address misinformation focus on a knowledge deficit model and propose interventions for improving users' critical thinking through access to facts. Such efforts are often hampered by challenges with scalability, and by platform users' personal biases. The emergence of generative AI presents promising opportunities for countering misinformation at scale across ideological barriers. In this paper, we introduce a framework (MisinfoEval) for generating and comprehensively evaluating large language model (LLM) based misinformation interventions. We present (1) an experiment with a simulated social media environment to measure effectiveness of misinformation interventions, and (2) a second experiment with personalized explanations tailored to the demographics and beliefs of users with the goal of countering misinformation by appealing to their pre-existing values. Our findings confirm that LLM-based interventions are highly effective at correcting user behavior (improving overall user accuracy at reliability labeling by up to 41.72%). Furthermore, we find that users favor more personalized interventions when making decisions about news reliability and users shown personalized interventions have significantly higher accuracy at identifying misinformation.
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。