EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

Read full text Summarise with VIRAT
Authors: Yujie Zhang, Weikang Yuan, Zhuoren Jiang, Pengwei Yan
Cited by: 0
References: 30

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Pluralistic alignment is essential for adapting large language models (LLMs) to the diverse preferences of individuals and minority groups.However, existing personalized reward models often mix stable personal traits with episodespecific factors, limiting their ability to generalize across episodes.To address this challenge, we propose EpiPersona, a framework for explicit persona-episode coupling.EpiPersona first projects noisy preference feedback into a low-dimensional persona space, where similar personas are aggregated into shared discrete codewords.This process separates enduring personal characteristics from situational signals without relying on predefined preference dimensions.The inferred persona representation is then coupled with the current episode, enabling episode-aware preference prediction.Extensive experiments show that EpiPersona outperforms the baselines.It achieves notable performance gains in hard episodic-shift scenarios, while remaining effective with sparse preference data.

Fields of Study & Subjects

Recommender Systems and Techniques Topic Modeling Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Pages
54804–54823
Publication date
1 January 2026
Language
EN