RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution.
Jiahui Li, Lin Li, Tai-Wei Chang, Kun Kuang, Long Chen, Jun Zhou, Cheng Yang
Browse the full EMNLP paper archive.
Jiahui Li, Lin Li, Tai-Wei Chang, Kun Kuang, Long Chen, Jun Zhou, Cheng Yang
Browse the full EMNLP paper archive.