{"type":"link","version":"1.0","title":"Training Language Models to Self-Correct via Reinforcement Learning","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/arxiv2409.12917","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2409.12917.png","thumbnail_width":1200,"thumbnail_height":630}