[2603.28197] EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

Computer Science > Artificial Intelligence arXiv:2603.28197 (cs) [Submitted on 30 Mar 2026] Title:EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling Authors:Yujie Zhang, Weikang Yuan, Zhuoren Jiang, Pengwei Yan View a PDF of the paper titled EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling, by Yujie Zhang and 3 other authors View PDF HTML (experimental) Abstract:Pluralistic alignment is essential for adapting large language models (LLMs) to the diverse preferences of individuals and minority groups. However, existing approaches often mix stable personal traits with episode-specific factors, limiting their ability to generalize across episodes. To address this challenge, we introduce 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 codes. 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 consistently outperforms the baselines. It achieves notable performance gains in hard episodic-shift scenarios, while remaining effective with sparse preference data. Subjects: Artificial Intelligence (cs.AI)...