# The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs

arXiv: https://arxiv.org/abs/2510.09905 · HTML: https://mlsanity.com/paper/2510.09905/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 17 of 17)

- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Human-inspired Episodic Memory for Infinite Context LLMs](https://mlsanity.com/paper/2407.09450/) (2024)
- [FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning](https://mlsanity.com/paper/2505.08054/) (2025)
- [Social Bias Evaluation for Large Language Models Requires Prompt Variations](https://mlsanity.com/paper/2407.03129/) (2024)
- [Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs](https://mlsanity.com/paper/2409.19401/) (2024)
- [Personalized LLM Response Generation with Parameterized Memory Injection](https://mlsanity.com/paper/2404.03565/) (2024)
- [User Embedding Model for Personalized Language Prompting](https://mlsanity.com/paper/2401.04858/) (2024)
- [LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education](https://mlsanity.com/paper/2410.14012/) (2024)
- [PersonaAgent: Bridging Memory and Action for Personalized LLM Agents](https://mlsanity.com/paper/2506.06254/) (2025)
- [Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective](https://mlsanity.com/paper/2506.19028/) (2025)

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

- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads](https://mlsanity.com/paper/2608.04570/) (2026)
- [The Company You Keep: How LLMs Respond to Dark Triad Traits](https://mlsanity.com/paper/2603.04299/) (2026)
- [DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models](https://mlsanity.com/paper/2607.02374/) (2026)
- [Inferring Hidden User Models from the Behavior of Personalized LLM Agents](https://mlsanity.com/paper/2609.03815/) (2026)
- [Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy](https://mlsanity.com/paper/2610.05162/) (2026)

## Abstract (arXiv)

When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI systems increasingly incorporate long-term user memory, understanding how this memory shapes emotional reasoning is critical. We investigate how user memory affects emotional intelligence in large language models (LLMs) by evaluating 15 models on human-validated emotional intelligence tests. We find that identical scenarios paired with different user profiles produce systematically divergent emotional interpretations. Across validated user-independent emotional scenarios and diverse user profiles, systematic biases emerged in several high-performing LLMs where advantaged profiles received more accurate emotional interpretations. Moreover, LLMs demonstrate significant disparities across demographic factors in emotion reasoning and supportive recommendations tasks, indicating that personalization mechanisms can embed social hierarchies into models' emotional reasoning. These results highlight a key challenge for memory-enhanced AI: systems designed for personalization may reinforce social inequalities. To mitigate these disparities, we curate a general-purpose preference dataset designed to reduce demographic profiles' influence on emotional understanding.