Pluralistic Off-policy Evaluation and Alignment

Abstract

Personalized preference alignment for LLMs with diverse human preferences requires evaluation and alignment methods that capture pluralism. Most existing preference alignment datasets are logged under policies that differ substantially from the evaluated LLMs, and existing off-policy estimators focus solely on overall utility while ignoring preference pluralism. Extending Off-Policy Evaluation (OPE) to pluralistic preference alignment, therefore, remains an open question. Thus, we propose the Pluralistic Off-Policy Evaluation (POPE), the first framework for offline pluralistic preference evaluation and alignment in LLMs. POPE includes a unified reward function that combines (1) a collaborative utility component derived from human preference signals (e.g., upvotes or relevance scores) and (2) a diversity component inspired by entropy-based coverage measures, together reflecting pluralistic alignment. Furthermore, to estimate this reward from logged interactions, we derive decomposable inverse propensity scoring (IPS) estimators that separately evaluate relevance and diversity. Theoretically, we prove that our decomposed IPS estimators establish a lower bound on their variance. With the off-policy evaluated value function, we can directly enable off-policy optimization to further enhance pluralistic alignment. Empirical results demonstrate that POPE efficiently enhances pluralistic response generation and maintains the models' general capabilities on downstream tasks