@inproceedings{wu-etal-2026-parallel,
    title = "Parallel-{SFT}: Improving Zero-Shot Cross-Programming-Language Transfer for Code {RL}",
    author = "Wu, Zhaofeng  and
      Wang, Shiqi  and
      Peng, Boya  and
      Goyal, Anuj Kumar  and
      Kambadur, Melanie  and
      Ruder, Sebastian  and
      Kim, Yoon  and
      Bi, Chloe",
    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.1324/",
    pages = "26583--26598",
    ISBN = "979-8-89176-395-1",
    abstract = "Modern language models demonstrate impressive coding capabilities in common programming languages (PLs), such as C++ and Python, but their performance in lower-resource PLs is often limited by training data availability. In principle, however, most programming skills are universal across PLs, so the capability acquired in one PL should transfer to others. In this work, we propose the task of zero-shot cross-programming-language transfer for code RL. We find that, for Llama-3.1, RL training for code generation in a source PL fails to improve, and sometimes even degrades, the performance on other target PLs. To address this, we hypothesize that effective RL transfer requires a generalizable SFT initialization before RL. We thus propose **Parallel-SFT**, an SFT strategy that incorporates ``parallel programs''{---}functionally equivalent code implemented in multiple PLs{---}into the data mixture. We demonstrate that this improves transferability: when we subsequently perform RL on our Parallel-SFT model, we observe better generalization to unseen PLs. Analysis of the model internal representations reveals that Parallel-SFT leads to a more functionality-centric latent space, where equivalent programs across PLs are more tightly clustered, which we hypothesize to contribute to the improved transferability."
}