{"type":"link","version":"1.0","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2305.18290","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2305.18290.png","thumbnail_width":1200,"thumbnail_height":630}