@inproceedings{su-etal-2026-reinforcement,
    title = "Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax",
    author = "Su, Zeli  and
      Zhang, Ziyin  and
      Liu, Zhou  and
      Song, Xuexian  and
      Xu, Zhankai  and
      Zheng, Longfei  and
      Zhang, Xiaolu  and
      Fu, Rong  and
      Xu, Guixian  and
      Zhang, Wentao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.880/",
    pages = "17772--17786",
    ISBN = "979-8-89176-395-1",
    abstract = "Extending large language models (LLMs) to low-resource languages often incurs an ``align- ment tax'': improvements in the target lan- guage come at the cost of catastrophic forget- ting in general capabilities. We argue that this trade-off arises from the rigidity of supervised fine-tuning (SFT), which enforces token-level surface imitation on narrow and biased data distributions. To address this limitation, we propose a semantic-space alignment paradigm powered by Group Relative Policy Optimiza- tion (GRPO), where the model is optimized us- ing embedding-level semantic rewards rather than likelihood maximization. This objective encourages meaning preservation through flex- ible realizations, enabling controlled updates that reduce destructive interference with pre- trained knowledge. We evaluate our approach on Tibetan{--}Chinese machine translation and Ti- betan headline generation. Experiments show that our method acquires low-resource capa- bilities while markedly mitigating alignment tax, preserving general competence more effec- tively than SFT. Despite producing less rigid surface overlap, semantic RL yields higher se- mantic quality and preference in open-ended generation, and few-shot transfer results indi- cate that it learns more transferable and ro- bust representations under limited supervision. Overall, our study demonstrates that reinforce- ment learning with semantic rewards provides a safer and more reliable pathway for inclusive low-resource language expansion."
}