{"type":"link","version":"1.0","title":"One reward model conditioned on a rule stated in text generalizes across many rules without a model per rule","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/rule-conditional-reward-model","thumbnail_url":"https://ai-arch.pages.dev/og/rule-conditional-reward-model.png","thumbnail_width":1200,"thumbnail_height":630}