# When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

arXiv: https://arxiv.org/abs/2601.11000 · HTML: https://mlsanity.com/paper/2601.11000/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2503.02450/) (2025)
- [Harnessing Large Language Models for Text-Rich Sequential Recommendation](https://mlsanity.com/paper/2403.13325/) (2024)
- [Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs](https://mlsanity.com/paper/2502.19148/) (2025)
- [Exploring Safety-Utility Trade-Offs in Personalized Language Models](https://mlsanity.com/paper/2406.11107/) (2024)
- [PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation](https://mlsanity.com/paper/2503.01303/) (2025)
- [Personalized LoRA for Human-Centered Text Understanding](https://mlsanity.com/paper/2403.06208/) (2024)
- [User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies](https://mlsanity.com/paper/2509.05382/) (2025)
- [Filter bubbles and affective polarization in user-personalized large language model outputs](https://mlsanity.com/paper/2311.14677/) (2023)
- [Benchmarking and Improving LLM Robustness for Personalized Generation](https://mlsanity.com/paper/2509.19358/) (2025)

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

- [The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads](https://mlsanity.com/paper/2608.04570/) (2026)
- [Mitigating LLM biases toward spurious social contexts using direct preference optimization](https://mlsanity.com/paper/2604.02585/) (2026)
- [Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy](https://mlsanity.com/paper/2610.05162/) (2026)

## Abstract (arXiv)

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries, there exists a phenomenon where the model generates answers aligned with a user's prior history rather than the objective truth, resulting in personalization-induced hallucinations that degrade factual reliability and may propagate incorrect beliefs, due to representational entanglement between personalization and factual representations. To address this issue, we propose Factuality-Preserving Personalized Steering (FPPS), a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. We further introduce PFQABench, the first benchmark designed to jointly evaluate factual and personalized question answering under personalization. Experiments across multiple LLM backbones and personalization methods show that FPPS substantially improves factual accuracy while maintaining personalized performance.