MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization
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.
ProofPaper ↗
Key points
- 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.
- 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.
Sources (1)
- [1]MoF: Preference-Aware Mixture Modeling for Black-Box LLM PersonalizationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 01:29 PM
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.
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.
Extractive summary: sentences quoted from the sources.