# EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

arXiv: https://arxiv.org/abs/2603.28197 · HTML: https://mlsanity.com/paper/2603.28197/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 24 of 24)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [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)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [Group Preference Optimization: Few-Shot Alignment of Large Language Models](https://mlsanity.com/paper/2310.11523/) (2023)
- [PersonalLLM: Tailoring LLMs to Individual Preferences](https://mlsanity.com/paper/2409.20296/) (2024)
- [Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models](https://mlsanity.com/paper/2407.07086/) (2024)
- [Personalized Generation In Large Model Era: A Survey](https://mlsanity.com/paper/2503.02614/) (2025)
- [A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications](https://mlsanity.com/paper/2503.17003/) (2025)
- [Personality Alignment of Large Language Models](https://mlsanity.com/paper/2408.11779/) (2024)
- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment](https://mlsanity.com/paper/2503.15463/) (2025)
- [Value Profiles for Encoding Human Variation](https://mlsanity.com/paper/2503.15484/) (2025)
- [SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs](https://mlsanity.com/paper/2506.05598/) (2025)
- [Cross-domain recommendation via user interest alignment](https://mlsanity.com/paper/2301.11467/) (2023)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas](https://mlsanity.com/paper/2501.11549/) (2025)
- [Selective Prompting Tuning for Personalized Conversations with LLMs](https://mlsanity.com/paper/2406.18187/) (2024)
- [ValueSim: Generating Backstories to Model Individual Value Systems](https://mlsanity.com/paper/2505.23827/) (2025)
- [Comparison-based Active Preference Learning for Multi-dimensional Personalization](https://mlsanity.com/paper/2411.00524/) (2024)

## Abstract (arXiv)

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.