分离用户长期人格与短期情境，提升大模型个性化推荐能力
EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling
- 将用户偏好映射到低维人格空间，自动聚类生成离散人格编码
- 在困难的跨场景迁移中性能显著优于基线，稀疏数据下仍有效
- 适合需要精准个性化推荐的场景，如对话系统、内容平台
多样化的偏好对齐对于使大语言模型适应不同个体和少数群体至关重要。然而，现有方法常将稳定的个人特质与特定情境因素混合，限制了跨场景泛化能力。为此，我们提出EpiPersona框架，实现显式的个性-事件耦合。EpiPersona首先将嘈杂的偏好反馈投影到低维人格空间，相似人格被聚合为共享的离散编码，从而在不依赖预定义偏好维度的前提下，分离持久性个人特征与情境信号。推断出的人格表征随后与当前事件耦合，实现事件感知的偏好预测。大量实验表明，EpiPersona持续优于基线，在困难的跨事件迁移场景中表现突出，且在稀疏偏好数据下依然有效。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。