{"title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","author_name":"NeurIPS 2023","author_url":"https://slideslive-test.dev/neurips-2023","type":"video","width":500,"height":199,"version":"1.0","provider_name":"SlidesLive","provider_url":"https://slideslive.com/","html":"<div id=\"slideslive:39014617\"></div>\n<script async type=\"application/javascript\" src=\"https://slideslive-test.dev/js_embed/presentations/39014617\"></script>","thumbnail_height":640,"thumbnail_width":640,"thumbnail_url":"https://ma.slideslive.com/library/presentations/39014617/thumbnail/direct-preference-optimization-your-language-model-is-secretly-a-reward-model_CJqWng_medium.png"}