Andre Wang He, Daniel Fried, Sean Welleck. Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 25548-25560, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.