ACL · 2026 · Conference paper

Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax

Zeli Su, Ziyin Zhang, Zhou Liu, Xuexian Song, Zhankai Xu, Longfei Zheng, Xiaolu Zhang, Rong Fu, Guixian Xu, Wentao Zhang

Minzu University of China · Shanghai Jiao Tong University · Peking University · Chinese Academy of Sciences · University of Macau · Hainan University

PDF from arXiv.HTML · PDF · Open in a new tab ↗ · Close
Published in
Findings of the Association for Computational Linguistics: ACL 2026
Date
2026-01-01
Citations
1
arXiv
2605.14366
Cite
@inproceedings{su2026reinforcement,
  title = {Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax},
  author = {Zeli Su and Ziyin Zhang and Zhou Liu and Xuexian Song and Zhankai Xu and Longfei Zheng and Xiaolu Zhang and Rong Fu and Guixian Xu and Wentao Zhang},
  year = {2026},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  eprint = {2605.14366},
  archivePrefix = {arXiv},
  doi = {10.18653/v1/2026.findings-acl.880},
  url = {https://arxiv.org/abs/2605.14366},
}