MMODELYST
Papers/Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity
PAP

Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity

May 9, 2026

arXiv
Abstract

Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions under which personalized alignment achieves O(1) online regret and log(1/epsilon) offline sample complexity. We show that these optimal rates depend on a specific user-diversity condition: the population of user-specific heads must span the latent reward directions that can alter the optimal response. We prove that this condition is both necessary and sufficient. When it holds, simple greedy algorithms achieve benchmark efficiency; when it fails, every learner in a natural admissible class incurs at least logarithmic regret. Our results identify user diversity as the fundamental driver of personalized identifiability.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Enoch Hyunwook Kang
Your notes (browser-local)
saved
arXiv:2605.09119