FirsthandTech
arXiv: cs.AI preprintsInternational20 November 2026

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

This is an official announcement record

Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2608.06400v2 Announce Type: replace Abstract: 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-
Source: arXiv: cs.AI preprints

More from arXiv: cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.