arXiv subjects

Jinyi Mu

Publications and source records attributed to Jinyi Mu.

2 recordsLinked to original sources

arXiv2026

Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast

Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging. Recent sparse Mixture-of-Experts (MoE) reward models seek to improve interpretability by routing prompts to specialized experts and characterizing experts through examples with high routing weights. However, routing weights only reveal which prompts an expert $\textit{receives}$, not how it $\textit{judges}$ responses, providing only a partial account of expert behavior. We therefore propose $\textbf{Co}$ntribution-$\textbf{Co}$ntrast ($\textbf{CoCo}$) response-level interpretation, which faithfully characterizes experts' roles using chosen-rejected response pairs with the largest contribution contrasts, jointly capturing routing and preference behavior. Across automatic and human evaluations, CoCo yields more coherent, faithful, and specialized interpretations than router-based, score-based, and sparse autoencoder-based alternatives while maintaining competitive reward modeling accuracy. To the best of our knowledge, this is the first systematic study of interpretation methods for MoE reward models.

cs.AI↗

arXiv2026

Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling

Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with human values. However, most existing approaches assume a universal reward function, neglecting the diversity and heterogeneity of human preferences. To address this limitation without additional annotation costs, recent work has proposed learning multiple preference components from binary data and combining them to model individual preferences. Nevertheless, these components often fail to capture coherent and disentangled patterns, limiting their interpretability and effectiveness for personalization. In this work, we propose a sparse Mixture-of-Experts (MoE) reward model that encourages sparse routing and expert diversity during training on binary preference data. Across controlled and real-world experiments, sparse MoE learns interpretable routing patterns and specialized experts. It also improves test-time personalization, and post-adaptation shifts in expert weights provide a qualitative lens for analyzing how the model adapts to personalized preferences.

cs.LG↗