@article{bo2026,
title = {VFPO: Variance-aware Negative Feedback Policy Optimization for Mitigating Entropy Collapse via Group Statistics},
author = {Zhang, Bo and Zeng, Zinan and Zhou, Juntong and Chong, Dading and Ding, Zhenyu and Wu, Dengpeng and Ding, Ning and Zhou, Peilin},
journal = {Findings of the Association for Computational Linguistics: EMNLP 2026},
year = {2026},
month = {Jan},
doi = {10.18653/2026.findings-emnlp.2449},
url = {https://doi.org/10.18653/2026.findings-emnlp.2449},
}
Zhang, Bo et al. (2026). VFPO: Variance-aware Negative Feedback Policy Optimization for Mitigating Entropy Collapse via Group Statistics. Findings of the Association for Computational Linguistics: EMNLP 2026. https://doi.org/10.18653/2026.findings-emnlp.2449
Zhang, Bo, et al.. "VFPO: Variance-aware Negative Feedback Policy Optimization for Mitigating Entropy Collapse via Group Statistics." Findings of the Association for Computational Linguistics: EMNLP 2026, 2026, https://doi.org/10.18653/2026.findings-emnlp.2449.
Zhang, Bo, et al.. "VFPO: Variance-aware Negative Feedback Policy Optimization for Mitigating Entropy Collapse via Group Statistics." Findings of the Association for Computational Linguistics: EMNLP 2026 (2026). https://doi.org/10.18653/2026.findings-emnlp.2449
Zhang, Bo et al., 2026. VFPO: Variance-aware Negative Feedback Policy Optimization for Mitigating Entropy Collapse via Group Statistics. Findings of the Association for Computational Linguistics: EMNLP 2026. Available at: <https://doi.org/10.18653/2026.findings-emnlp.2449>.
TY - JOUR
TI - VFPO: Variance-aware Negative Feedback Policy Optimization for Mitigating Entropy Collapse via Group Statistics
AU - Zhang, Bo
AU - Zeng, Zinan
AU - Zhou, Juntong
AU - Chong, Dading
AU - Ding, Zhenyu
AU - Wu, Dengpeng
AU - Ding, Ning
AU - Zhou, Peilin
PY - 2026
JO - Findings of the Association for Computational Linguistics: EMNLP 2026
DO - 10.18653/2026.findings-emnlp.2449
UR - https://doi.org/10.18653/2026.findings-emnlp.2449
ER -