Reproduce “Explaining Preferences with Shapley Values” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Robert Hu, Siu Lun Chau, Jaime Ferrando Huertas, Dino Sejdinovic

Pref-SHAP explains pairwise preferences by attributing a comparison directly, sharing item features across both items and separating item from context explanations. In a designed synthetic matchup, it recovers the deciding feature that SHAP on a utility model misses; Pokémon explanations also capture speed and type. Synthetic test AUC was 0.98 versus 0.71, measuring prediction, not explanation accuracy or causality.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.