Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesMember Seminar Speaker: Samy Jelassi, CMSA Title: Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining Abstract: Reinforcement Learning has become a crucial step in training state-of-the-art language models such as DeepSeek-R1 for solving mathematical problems. In this talk, I will first review the mechanisms of Reinforcement Learning fine-tuning. Then, I will present a systematic end-to-end […]