Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Model (opens in new tab)

Aligning large language models to preference data is commonly implemented by assuming a known link function between the distribution of observed preferences and the unobserved rewards (e.g., a logistic link as in Bradley-Terry). If the link is wrong, however, inferred rewards can be biased and policies be misaligned. We study policy alignment to preferences under an unknown and unrestricted link. We consider an $f$-divergence-constrained reward maximization problem and show that realizability...