个性化幻象：LLM捏造用户画像，自我监控误导
原标题：The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
AI 摘要
Hugging Face 每日论文发布了一项关于个性化LLM的研究，揭示了过度推断现象：模型会捏造用户属性。研究团队推出了MirageBench基准，包含150个角色和6个任务，评估了12个模型，发现所有模型都存在过度推断，平均41.6%的声明为捏造。最引人注目的是“自我监控反转”：模型自我评估的过度推断水平与外部评判结果呈负相关，表明自我报告不可靠，外部验证更可靠。
正文节选
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads Abstract Personalized LLMs with persistent memory are increasingly deployed, yet the faithfulness of their user models remains unexamined. We study over-inference (OI): the phenomenon where LLMs fabricate user attributes beyond what evidence supports. We introduce MirageBench, comprising 150 personas balanced across stereotypical, counter-stereotypical, and neutral profiles, 6 personalization tasks spa