One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Sep 30, 2025·
,
,
,
·
0 min read
Rui Ming
Haoyuan Wu
Shoubo Hu
Zhuolun He
Bei Yu
Type
Publication
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026, Findings)
