FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
This work focuses on a practical yet challenging setting where only a small set of preference annotations can be collected per user, and proposes FaST, a highly parameter-efficient approach that leverages high-level features automatically discovered from the data, achieving the best overall performance.
Thibaut Thonet, Germán Kruszewski, Jos Rozen et al.
· Conference on Empirical Meth... · 5 citations