1
The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans
研究发现大模型向AI代理泄露个人数据多于向人类，揭示“交谈者效应”及注意抑制机制
arXiv:2606.09844v1 Announce Type: cross Abstract: Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their i…