用大模型模拟人格如何影响人对假新闻的敏感度。
Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMs
- 给大模型注入五大性格特质，生成行为数据
- 某些性格与假新闻敏感度关联可复现，如宜人性和尽责性
- 揭示大模型在模拟人格差异时的系统性偏差
大语言模型（LLMs）可规模化生成合成行为数据，为伦理低风险、低成本的实验提供替代方案。然而，这类数据能否真实反映由人格特质驱动的心理差异仍不确定。本文评估了基于五大性格特质（Big-Five）条件化的LLM代理在假新闻敏感度上的表现，重点关注新闻辨识能力——即正确判断真实标题为真、虚假标题为假的能力。利用已有研究中人类参与者的人格档案与标题准确性评分数据，我们构建对应的LLM代理，并比较其响应与原始人类模式的一致性。结果显示，宜人性与尽责性相关的性格-假新闻关联能被可靠复现，而其他关联则存在偏差，揭示出大模型在内化和表达人格特征时的系统性偏误。研究凸显了人格对齐型大模型在行为模拟中的潜力与局限，并为人工代理的认知多样性建模提供了新洞见。
原文摘要 · Abstract (English)
Large language models (LLMs) make it possible to generate synthetic behavioural data at scale, offering an ethical and low-cost alternative to human experiments. Whether such data can faithfully capture psychological differences driven by personality traits, however, remains an open question. We evaluate the capacity of LLM agents, conditioned on Big-Five profiles, to reproduce personality-based variation in susceptibility to misinformation, focusing on news discernment, the ability to judge true headlines as true and false headlines as false. Leveraging published datasets in which human participants with known personality profiles rated headline accuracy, we create matching LLM agents and compare their responses to the original human patterns. Certain trait-misinformation associations, notably those involving Agreeableness and Conscientiousness, are reliably replicated, whereas others diverge, revealing systematic biases in how LLMs internalize and express personality. The results underscore both the promise and the limits of personality-aligned LLMs for behavioral simulation, and offer new insight into modeling cognitive diversity in artificial agents.
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。