@article{haoran2026,
title = {Escaping the KL Agreement Trap in On-Policy Distillation},
author = {Xin, Haoran and Zhao, Anhao and Sun, Ying and Li, Jin and Shen, Xiaoyu and Xiong, Hui},
journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
year = {2026},
month = {Jan},
doi = {10.18653/2026.emnlp-main.1817},
url = {https://doi.org/10.18653/2026.emnlp-main.1817},
}
Xin, Haoran et al. (2026). Escaping the KL Agreement Trap in On-Policy Distillation. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/2026.emnlp-main.1817
Xin, Haoran, et al.. "Escaping the KL Agreement Trap in On-Policy Distillation." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026, https://doi.org/10.18653/2026.emnlp-main.1817.
Xin, Haoran, et al.. "Escaping the KL Agreement Trap in On-Policy Distillation." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026). https://doi.org/10.18653/2026.emnlp-main.1817
Xin, Haoran et al., 2026. Escaping the KL Agreement Trap in On-Policy Distillation. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. Available at: <https://doi.org/10.18653/2026.emnlp-main.1817>.
TY - JOUR
TI - Escaping the KL Agreement Trap in On-Policy Distillation
AU - Xin, Haoran
AU - Zhao, Anhao
AU - Sun, Ying
AU - Li, Jin
AU - Shen, Xiaoyu
AU - Xiong, Hui
PY - 2026
JO - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
DO - 10.18653/2026.emnlp-main.1817
UR - https://doi.org/10.18653/2026.emnlp-main.1817
ER -