用信念模型模拟不同人群对谣言的敏感度，提升社会风险预测能力。
Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility
- 基于心理学分类和调查数据构建人群信念画像
- 信念驱动模拟使敏感度预测准确率达92%
- 适合研究谣言传播与群体心理的学者使用
虚假信息是日益严重的社会威胁，不同人口群体对误导性言论的敏感度因内在信念差异而异。随着大语言模型（LLMs）被广泛用于模拟人类行为，我们探讨其是否可用来模拟人口层面的虚假信息敏感度，并将信念视为核心驱动因素。本文提出BeliefSim框架，利用心理学指导的虚假信息分类体系和调查先验信息构建人口信念画像。研究了提示词引导与微调适应策略，并通过双重评估：(i) 敏感度一致性与 (ii) 反事实人口敏感性，在多个数据集和建模方法下验证。结果表明，信念作为强先验，显著提升了虚假信息敏感度的模拟效果，一致性最高达92%。
原文摘要 · Abstract (English)
Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic groups due to differences in underlying beliefs. As Large Language Models (LLMs) are increasingly used to simulate human behaviors, we investigate whether they can simulate demographic misinformation susceptibility, treating beliefs as a primary driving factor. We introduce BeliefSim, a simulation framework that constructs demographic belief profiles using psychology-informed misinformation taxonomies and survey priors. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility alignment and (ii) counterfactual demographic sensitivity. Across both datasets and modeling strategies, we show that beliefs provide a strong prior for simulating misinformation susceptibility, with alignment up to 92%.
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。