🧑🔬 Josef Dai — papers of 2023 — 1 paper, the most cited first1 paper · all years of Josef DaiSafe RLHF: Safe Reinforcement Learning from Human FeedbackarXiv:2310.12773Josef Dai, Xuehai Pan, Ruiyang Sun, et al.2023 · 217 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/josef-dai/year/2023/