MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization

arXiv:2610.08330 · cs.AI · Submitted 2026-10-06 · Read on arXiv

cs.AI

Submitted: 2026-10-06

Updated: 2026-10-06

Code: https://github.com/hoonpak/Mixture-of-Facets

Terminology

• Personalization — 1× in this paper · explained in 2 episodes

Sources

• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• BERTopic: Neural topic modeling with a class-based TF-IDF procedure
• Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• GPT-4 Technical Report
• FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning
• Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems