Search Results for author: Nahyeon Ryu

Found 1 papers, 1 papers with code

Aligning Language Models with Preferences through f-divergence Minimization

1 code implementation16 Feb 2023 Dongyoung Go, Tomasz Korbak, Germán Kruszewski, Jos Rozen, Nahyeon Ryu, Marc Dymetman

We show that Jensen-Shannon divergence strikes a good balance between these objectives, and frequently outperforms forward KL divergence by a wide margin, leading to significant improvements over prior work.

Cannot find the paper you are looking for? You can Submit a new open access paper.