@inproceedings{yu-etal-2026-need,
    title = "You Only Need One Single Token to Refine Safety Alignment",
    author = "Yu, Wenqian  and
      Chen, Shuo  and
      Li, Zhijiang  and
      Wang, Zhipeng  and
      Gu, Jindong",
    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.662/",
    pages = "13529--13545",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) face a critical alignment challenge: balancing safety with helpfulness. Excessive safety can lead to over-refusal, where models reject harmful-looking yet benign queries, severely limiting utility.Existing training-free interventions offer an efficient way to mitigate over-refusal without re-training, but suffer from high inference overhead and architecture dependency. Our work explores a complementary direction: rather than applying post-hoc corrections to model outputs, our goal is to intrinsically reshape the distributions of harmful and benign samples within the model{'}s decision space. In this paper, we argue that a lightweight training-based approach can more effectively distinguish between harmful and benign samples. We propose Single Token Alignment (STA), which optimizes only a single-token prefix (e.g., 4,096 parameters) while keeping the base model frozen. To address the inherent challenge of achieving robust refinement through such a minimal parameter interface, STA employs a mixed weighting mechanism integrated with its optimization objective. This mechanism incorporates hard weighting via stringent data filtering to provide clear, unbiased learning signals, and soft weighting through a focal mechanism to prioritize challenging cases.Extensive experiments across 9 models and 10 datasets demonstrate that STA achieves a superior safety-helpfulness balance for LLMs, MLLMs, and reasoning models, offering a highly efficient and generalizable solution for refining safety alignment."
}