# Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory

arXiv: https://arxiv.org/abs/2508.07664 · HTML: https://mlsanity.com/paper/2508.07664/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2025.

## Built on by (most cited first, 6 of 6)

- [MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents](https://mlsanity.com/paper/2605.09530/) (2026)
- [Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference](https://mlsanity.com/paper/2509.12152/) (2025)
- [Prioritize Economy or Climate Action? Investigating ChatGPT Response Differences Based on Inferred Political Orientation](https://mlsanity.com/paper/2511.04706/) (2025)
- [Understanding U.S. Users' Security and Privacy Transparency Needs for Consumer-Facing Generative AI](https://mlsanity.com/paper/2604.17270/) (2026)
- [Focused on the User, Overlooking the Risks: Security and Privacy Understandings, Practices and Challenges of Independent Chinese AI Agent Developers](https://mlsanity.com/paper/2606.03190/) (2026)
- [From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study](https://mlsanity.com/paper/2609.16344/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly integrating memory functionalities to provide personalized and context-aware interactions. However, user understanding, practices and expectations regarding these memory systems are not yet well understood. This paper presents a thematic analysis of semi-structured interviews with 18 users to explore their mental models of LLM's Retrieval Augmented Generation (RAG)-based memory, current usage practices, perceived benefits and drawbacks, privacy concerns and expectations for future memory systems. Our findings reveal diverse and often incomplete mental models of how memory operates. While users appreciate the potential for enhanced personalization and efficiency, significant concerns exist regarding privacy, control and the accuracy of remembered information. Users express a desire for granular control over memory generation, management, usage and updating, including clear mechanisms for reviewing, editing, deleting and categorizing memories, as well as transparent insight into how memories and inferred information are used. We discuss design implications for creating more user-centric, transparent, and trustworthy LLM memory systems.