@article{yuanda2026,
title = {Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training},
author = {Xu, Yuanda and Sang, Hejian and Zhou, Zhengze and He, Ran and Wang, Zhipeng and Geramifard, Alborz},
journal = {Findings of the Association for Computational Linguistics: EMNLP 2026},
year = {2026},
month = {Jan},
doi = {10.18653/2026.findings-emnlp.639},
url = {https://doi.org/10.18653/2026.findings-emnlp.639},
}
Xu, Yuanda et al. (2026). Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training. Findings of the Association for Computational Linguistics: EMNLP 2026. https://doi.org/10.18653/2026.findings-emnlp.639
Xu, Yuanda, et al.. "Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training." Findings of the Association for Computational Linguistics: EMNLP 2026, 2026, https://doi.org/10.18653/2026.findings-emnlp.639.
Xu, Yuanda, et al.. "Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training." Findings of the Association for Computational Linguistics: EMNLP 2026 (2026). https://doi.org/10.18653/2026.findings-emnlp.639
Xu, Yuanda et al., 2026. Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training. Findings of the Association for Computational Linguistics: EMNLP 2026. Available at: <https://doi.org/10.18653/2026.findings-emnlp.639>.
TY - JOUR
TI - Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
AU - Xu, Yuanda
AU - Sang, Hejian
AU - Zhou, Zhengze
AU - He, Ran
AU - Wang, Zhipeng
AU - Geramifard, Alborz
PY - 2026
JO - Findings of the Association for Computational Linguistics: EMNLP 2026
DO - 10.18653/2026.findings-emnlp.639
UR - https://doi.org/10.18653/2026.findings-emnlp.639
ER -