Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
Publication information:
R. Zhao*, A. Meterez*, S. Kakade, C. Pehlevan, S. Jelassi, and E. Malach,
“Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining”, The Conference on Language Modeling (COLM), 2025.