🧑🔬 Misha Khalman — papers of 20232 papers · all years of Misha KhalmanSLiC-HF: Sequence Likelihood Calibration with Human FeedbackYao Zhao, Rishabh Joshi, Tianqi Liu, et al.arXiv:2305.10425 · 135 citationsStatistical Rejection Sampling Improves Preference OptimizationTianqi Liu, Yao Zhao, Rishabh Joshi, et al.arXiv:2309.06657 · 101 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/misha-khalman/year/2023/