arXiv：cs.AI· Hun Park·· 6 小时前AI 评分32
MoF：面向黑盒 LLM 个性化的偏好感知混合建模
MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization
AI 导读
研究者提出 Mixture-of-Facets（MoF），一种面向黑盒 LLM 的可扩展个性化框架，将用户偏好建模为共享潜在偏好分面的组合，而非专属的用户参数。
正文
Abstract:Proprietary Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet aligning their outputs with diverse user preferences remains challenging. Existing personalization approaches for black-box LLMs often rely on user-specific scoring heads, causing the number of personalized parameters to grow linearly with the number of users and requiring additional adaptation for unseen users. To address these limitations, we propose Mixture-of-Facets (MoF), a scalable personalization framework for black-box LLMs that models user preferences as compositions of shared latent preference facets rather than dedicated user-specific parameters. MoF performs personalization through history-conditioned routing over shared facet heads, enabling personalization for users unseen during training without additional parameter updates. Across diverse personalization tasks, MoF delivers stronger personalization performance while maintaining a more scalable and parameter-efficient design than prior approaches. Additional analysis indicates strong generalization to unseen users.
| Comments: | Accepted at EMNLP 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08330 [cs.AI] |
| (or arXiv:2610.08330v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08330 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hun Park [view email]
[v1]
Tue, 6 Oct 2026 13:29:26 UTC (13,893 KB)
来源：arXiv：cs.AI · arxiv.org