Kyuyoung Kim Ah Jeong Seo Hao Liu Jinwoo Shin Kimin Lee Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback. 2024 abs/2410.03145 CoRR https://doi.org/10.48550/arXiv.2410.03145 db/journals/corr/corr2410.html#abs-2410-03145 streams/journals/corr