# The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans

arXiv: https://arxiv.org/abs/2606.09844 · HTML: https://mlsanity.com/paper/2606.09844/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 13 of 13)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation](https://mlsanity.com/paper/2510.15186/) (2025)
- [Securing the Model Context Protocol (MCP): Risks, Controls, and Governance](https://mlsanity.com/paper/2511.20920/) (2025)
- [Searching for Privacy Risks in LLM Agents via Simulation](https://mlsanity.com/paper/2508.10880/) (2025)
- [Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation](https://mlsanity.com/paper/2512.16310/) (2025)
- [OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage](https://mlsanity.com/paper/2602.13477/) (2026)

## Built on by (most cited first, 1 of 1)

- [Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems](https://mlsanity.com/paper/2609.39050/) (2026)

## Abstract (arXiv)

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 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 interactions with agents. We assess this quantitatively by comparing human-directed and agent-directed prompts in 222 sensitive scenarios. Our findings, drawn from 3,464 interactions, indicate that portraying the recipient as an AI agent elevates PII leakage by up to 23 percentage points. Initial experiments on Llama-3.1-8B-Instruct corroborate this: deactivating one safety head induces leakage, whereas reactivating it reinstates privacy safeguards. We consider the implications for developing secure multi-agent systems.