When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning

Yijiang River Dong, Tiancheng Hu, Yinhong Liu, Ahmet Üstün, Nigel Collier


Abstract
While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority viewpoints.Although personalized preference learning addresses this by tailoring separate preferences for individual users, the field lacks standardized methods to assess its effectiveness. We present a multi-faceted evaluation framework that measures not only performance but also fairness, unintended effects, and adaptability across varying levels of preference divergence. Through extensive experiments comparing eight personalization methods across three preference datasets, we demonstrate that performance differences between methods could reach 36% when users strongly disagree, and personalization can introduce up to 20% safety misalignment. These findings highlight the critical need for holistic evaluation approaches to advance the development of more effective and inclusive preference learning systems.
Anthology ID:
2025.findings-emnlp.916
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16880–16894
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.916/
DOI:
Bibkey:
Cite (ACL):
Yijiang River Dong, Tiancheng Hu, Yinhong Liu, Ahmet Üstün, and Nigel Collier. 2025. When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16880–16894, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning (Dong et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.916.pdf
Checklist:
 2025.findings-emnlp.916.checklist.pdf