@inproceedings{liu-etal-2026-profit,
    title = "{P}ro{F}it: Leveraging High-Value Signals in {SFT} via Probability-Guided Token Selection",
    author = "Liu, Tao  and
      Wu, Taiqiang  and
      Yang, Runming  and
      Sun, Shaoning  and
      Wang, Junjie  and
      Yang, Yujiu",
    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.755/",
    pages = "15383--15401",
    ISBN = "979-8-89176-395-1",
    abstract = "Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the $\textit{one-to-many}$ nature of language by forcing alignment with a single reference answer, leading to the model overfitting to non-core expressions. Although our empirical analysis suggests that introducing multiple reference answers can mitigate this issue, the prohibitive data and computational costs necessitate a strategic shift: prioritizing the mitigation of single-reference overfitting over the costly pursuit of answer diversity. To achieve this, we reveal the intrinsic connection between token probability and semantic importance: high-probability tokens carry the core logical framework, while low-probability tokens are mostly replaceable expressions. Based on this insight, we propose $\textbf{ProFit}$, which selectively masks low-probability tokens to prevent surface-level overfitting. Extensive experiments confirm that ProFit consistently outperforms traditional SFT baselines on general reasoning and mathematical benchmarks"
}