用大模型模拟假信息在社交网络中的传播，揭示认知偏见如何加速谣言扩散。
Simulating Misinformation Propagation in Social Networks using Large Language Models
- 用大模型角色模拟用户偏见和立场，构建可追踪的传播代理
- 30轮重写后，身份导向角色使事实偏差提升至传播级扭曲
- 适合研究假信息机制、平台治理与可信内容评估的学者
社交媒体上的假信息依赖意外性、情绪和身份驱动推理，常因人类认知偏见而被放大。为研究这些机制，我们建模大型语言模型（LLM）人格作为合成代理，模拟用户层面的偏见、意识形态倾向和信任启发式。在此框架下，提出审计-节点结构，模拟并分析假信息在代理网络中传播时的演化过程。新闻内容在人格条件化的LLM节点间传播，每个节点重写接收到的内容。基于问答的审计器在每一步测量事实保真度，实现可解释的逐条追踪。我们形式化了假信息指数和假信息传播率，量化了最多30次连续重写中同质与异质分支的事实退化。10个领域中21种人格的实验表明，身份与意识形态导向的人格是假信息加速器，尤其在政治、营销和技术领域；而专家型人格则保持事实稳定。受控随机分支模拟显示，一旦早期失真出现，异质人格交互会迅速将假信息升级为宣传级扭曲。我们提出的假信息严重性分类——涵盖事实错误、谎言和宣传——将观测到的漂移与假信息研究中的既有理论相连接。结果表明，LLM兼具人类偏见代理与事实追踪审计器的双重角色。该框架为研究、模拟和缓解数字生态中的假信息扩散提供了可解释、实证基础的方法。
原文摘要 · Abstract (English)
Misinformation on social media thrives on surprise, emotion, and identity-driven reasoning, often amplified through human cognitive biases. To investigate these mechanisms, we model large language model (LLM) personas as synthetic agents that mimic user-level biases, ideological alignments, and trust heuristics. Within this setup, we introduce an auditor--node framework to simulate and analyze how misinformation evolves as it circulates through networks of such agents. News articles are propagated across networks of persona-conditioned LLM nodes, each rewriting received content. A question--answering-based auditor then measures factual fidelity at every step, offering interpretable, claim-level tracking of misinformation drift. We formalize a misinformation index and a misinformation propagation rate to quantify factual degradation across homogeneous and heterogeneous branches of up to 30 sequential rewrites. Experiments with 21 personas across 10 domains reveal that identity- and ideology-based personas act as misinformation accelerators, especially in politics, marketing, and technology. By contrast, expert-driven personas preserve factual stability. Controlled-random branch simulations further show that once early distortions emerge, heterogeneous persona interactions rapidly escalate misinformation to propaganda-level distortion. Our taxonomy of misinformation severity -- spanning factual errors, lies, and propaganda -- connects observed drift to established theories in misinformation studies. These findings demonstrate the dual role of LLMs as both proxies for human-like biases and as auditors capable of tracing information fidelity. The proposed framework provides an interpretable, empirically grounded approach for studying, simulating, and mitigating misinformation diffusion in digital ecosystems.
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。