aiqbench analysis
This paper introduces Mixture-of-Facets (MoF), a scalable framework for personalizing black-box LLMs by decomposing user preferences into shared latent facets rather than maintaining linearly growing user-specific parameters. By utilizing history-conditioned routing over these shared heads, the method achieves strong generalization to unseen users without requiring additional adaptation or parameter updates. This approach directly addresses the efficiency and scalability bottlenecks inherent in current personalization techniques for proprietary models.
MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization
arXiv:2610.08330v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI)
arXiv:2610.08330 [cs.AI]
(or arXiv:2610.08330v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.08330 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 232 words
Related coverage
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
arXiv · Sep 16, 2026
My AI Slavery Interviews Are Censored On LW By Default
LessWrong · Jul 27, 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026