🧑🔬 Haitao Mi — papers of 2023 — 1 paper, the most cited first1 paper · all years of Haitao MiThe Trickle-down Impact of Reward (In-)consistency on RLHFarXiv:2309.16155Lingfeng Shen, Sihao Chen, Linfeng Song, et al.2023 · 11 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/haitao-mi/year/2023/