# Mitigating Over-Personalization in LLMs via Structured Memory

arXiv: https://arxiv.org/abs/2608.08300 · HTML: https://mlsanity.com/paper/2608.08300/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Builds on (most cited first, 27 of 27)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control](https://mlsanity.com/paper/2505.18279/) (2025)
- [REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation](https://mlsanity.com/paper/2502.13270/) (2025)
- [Contextual Integrity in LLMs via Reasoning and Reinforcement Learning](https://mlsanity.com/paper/2506.04245/) (2025)
- [Interaction Context Often Increases Sycophancy in LLMs](https://mlsanity.com/paper/2509.12517/) (2025)
- [CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs](https://mlsanity.com/paper/2511.14937/) (2025)
- [Prompt Leakage effect and defense strategies for multi-turn LLM interactions](https://mlsanity.com/paper/2404.16251/) (2024)
- [PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?](https://mlsanity.com/paper/2602.01146/) (2026)
- [Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework](https://mlsanity.com/paper/2604.01707/) (2026)
- [Mitigating Memorization in LLMs using Activation Steering](https://mlsanity.com/paper/2503.06040/) (2025)
- [Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models](https://mlsanity.com/paper/2601.15220/) (2026)

## Built on by (most cited first, 3 of 3)

- [PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use](https://mlsanity.com/paper/2609.34526/) (2026)
- [Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy](https://mlsanity.com/paper/2610.05162/) (2026)
- [What to Admit and How to Present: Governing Persistent Memory in LLM Agents](https://mlsanity.com/paper/2610.11188/) (2026)

## Abstract (arXiv)

Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions. However, when stored user information is reintroduced into the model context, it can also influence responses in inappropriate or unrelated settings. We study two such failure modes in memory-augmented LLMs: cross-domain leakage, where memories from one life domain affect responses in another, and memory-induced sycophancy, where stored user beliefs make models more likely to agree with the user rather than respond truthfully. We apply a simple inference-time modification to how memories are presented to the model, without changing the model or the memory contents. Across seven models on PersistBench, we compare the commonly used all-in context format, where memories are injected as an unstructured list, with structured formats that partition memories by domain. This simple modification consistently reduces cross-domain leakage while preserving utility, with our strongest method reducing leakage by 8.8% on average relative to the baseline.