@inproceedings{zeng-etal-2026-racc,
    title = "{RACC}: Regret-Aware Confidence Calibration for Consistent Masked Discrete Diffusion Decoding",
    author = "Zeng, Qinglin  and
      Zhang, Jusheng  and
      Yang, Jing  and
      Liu, Ningyuan  and
      Wang, Keze",
    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.1138/",
    pages = "22656--22672",
    ISBN = "979-8-89176-395-1",
    abstract = "Masked Discrete Diffusion Models (MDMs) enable parallel generation via iterative refinement. However, we identify a critical decisional mismatch. The MDM architecture is inherently dynamic and capable of sensing context shifts. In contrast, prevailing decoding paradigms remain static and myopic. They treat each denoising step as an isolated snapshot, effectively discarding valuable temporal feedback that signals logical conflicts. To bridge this gap, we propose Regret-Aware Confidence Calibration (RACC). This training-free framework aligns decoding decisions with the model{'}s latent self-correction capabilities. RACC introduces a momentum anchor to track confidence trajectories. When a token{'}s probability drops abruptly below its historical trend, the system triggers a ``regret'' signal. Unlike expensive re-masking or lookahead search, RACC utilizes this signal to proactively demote unstable candidates. Extensive experiments on reasoning benchmarks, such as HumanEval and GSM8K, demonstrate that RACC significantly improves generation consistency. Crucially, RACC achieves these gains with zero additional inference overhead, effectively balancing decoding quality and efficiency."
}