RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation

TL;DR

This paper advances RLHF by developing frameworks to handle diverse human preferences through personalization and aggregation, with theoretical guarantees and strategies to ensure truthful feedback in heterogeneous settings.

Contribution

It introduces novel methods for modeling and aggregating heterogeneous human feedback in RLHF, including personalization, reward models, and truthful preference aggregation with strategic behavior considerations.

Findings

Proposes personalization-based reward models with sample complexity guarantees.

Develops aggregation methods for diverse preferences with theoretical analysis.

Designs mechanisms to ensure truthful feedback from strategic human labelers.

Abstract

Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values, with remarkable successes in fine-tuning large-language models recently. Most existing RLHF paradigms make the underlying assumption that human preferences are relatively homogeneous, and can be encoded by a single reward model. In this paper, we focus on addressing the issues due to the inherent heterogeneity in human preferences, as well as their potential strategic behavior in providing feedback. Specifically, we propose two frameworks to address heterogeneous human feedback in principled ways: personalization-based one and aggregation-based one. For the former, we propose two approaches based on representation learning and clustering, respectively, for learning multiple reward models that trades off the bias (due to preference heterogeneity) and variance (due to the use of fewer data for learning each model by personalization). We then establish sample complexity guarantees for both approaches. For the latter, we aim to adhere to the single-model framework, as already deployed in the current RLHF paradigm, by carefully aggregating diverse and truthful preferences from humans. We propose two approaches based on reward and preference aggregation, respectively: the former utilizes both utilitarianism and Leximin approaches to aggregate individual reward models, with sample complexity guarantees; the latter directly aggregates the human feedback in the form of probabilistic opinions. Under the probabilistic-opinion-feedback model, we also develop an approach to handle strategic human labelers who may bias and manipulate the aggregated preferences with untruthful feedback. Based on the ideas in mechanism design, our approach ensures truthful preference reporting, with the induced aggregation rule maximizing social welfare functions.