Molecular language modeling is an effective approach to generating novel chemical structures. However, these models do not \emph{a priori} encode certain preferences a chemist may desire. We investigate the use of fine-tuning using Direct Preference Optimization to better align generated molecules with chemist preferences. Our findings suggest that this approach is simple, efficient, and highly effective.
@article{arxiv.2310.12304,
title = {Preference Optimization for Molecular Language Models},
author = {Ryan Park and Ryan Theisen and Navriti Sahni and Marcel Patek and Anna Cichońska and Rayees Rahman},
journal= {arXiv preprint arXiv:2310.12304},
year = {2023}
}