{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/efde43f4-715f-4566-a26d-178b7576d842\" width=\"1280\" height=\"720\" title=\"An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/efde43f4-715f-4566-a26d-178b7576d842/episode.poster.webp","title":"An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning","type":"video","version":"1.0","width":1280}