消解事实默认：对人类在真实世界中对基础模型幻觉和虚假信息易感性的因果分析
Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild
AI总结：
本文通过双轴框架分析人类对基础模型幻觉和虚假信息的易感性，发现假新闻熟悉度是关键中介，提出应通过提升认知来源监控来确保信息可信。
摘要：
随着基础模型（FMs）接近人类水平的流畅性，区分合成内容与有机内容已成为可信网络智能的关键挑战。本文提出了JudgeGPT和RogueGPT，一种双轴框架，将“真实性”与“归属”解耦，以研究人类易感性机制。分析了五个基础模型（包括GPT-4和Llama-2）的918次评估，我们采用结构因果模型（SCMs）作为主要框架，以制定可检验的因果假设，探讨检测准确率。与偏见叙述相反，我们发现政治倾向与检测性能之间几乎没有关联（r=-0.10）。相反，“假新闻熟悉度”作为一种候选中介（r=0.35）出现，表明暴露可能作为对抗性训练用于人类判别器。我们识别出一个“流畅陷阱”，其中GPT-4输出（HumanMachineScore: 0.20）绕过来源监控机制，使其与人类文本难以区分。这些发现表明，“预欺骗”干预应针对认知来源监控而非人口统计学分割，以确保可信的信息生态系统。
英文摘要：
As foundation models (FMs) approach human-level fluency, distinguishing synthetic from organic content has become a key challenge for Trustworthy Web Intelligence. This paper presents JudgeGPT and RogueGPT, a dual-axis framework that decouples "authenticity" from "attribution" to investigate the mechanisms of human susceptibility. Analyzing 918 evaluations across five FMs (including GPT-4 and Llama-2), we employ Structural Causal Models (SCMs) as a principal framework for formulating testable causal hypotheses about detection accuracy. Contrary to partisan narratives, we find that political orientation shows a negligible association with detection performance ($r=-0.10$). Instead, "fake news familiarity" emerges as a candidate mediator ($r=0.35$), suggesting that exposure may function as adversarial training for human discriminators. We identify a "fluency trap" where GPT-4 outputs (HumanMachineScore: 0.20) bypass Source Monitoring mechanisms, rendering them indistinguishable from human text. These findings suggest that "pre-bunking" interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy information ecosystems.
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。
