The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans
Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor. While safety mechanisms typically prevent LLMs from releasing Personally Identifiable Information (PII) to human users, these models tend to reveal more sensitive data when addressing another AI agent. We refer to this as the \textbf{Interlocutor Effect}. Through an ablation study, we find evidence that the technical nature of the recipient contributes to this effect, thereby diminishing the model's caution regarding privacy. To explore this further, we introduce the Attention Suppression Hypothesis, which posits that safety-aligned attention heads become inactive during intera...
| Authors | Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah |
|---|---|
| Primary category | cs.HC |
| Published | 26 April 2026 |
| Last updated at source | 26 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.