@inproceedings{park-etal-2026-pure,
    title = "{PURE}: Post-hoc Unlocking and {RE}finement for Discrete Diffusion Decoding",
    author = "Park, Yangryeol  and
      Lee, Kunhui  and
      Choi, Hanback  and
      Park, Cheoneum  and
      Jeon, Donghyeon  and
      Kang, Inho  and
      Na, Seung-Hoon",
    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.1234/",
    pages = "24653--24667",
    ISBN = "979-8-89176-395-1",
    abstract = "Masked diffusion language models (MDLMs) enable efficient parallel decoding but are limited by a monotonic unmasking policy, where committed tokens cannot be revised. While remasking-based methods mitigate early errors, they mainly intervene during generation. In this work, we study post-hoc refinement of a completed draft and find that naive correction often fails because of contextual lock-in, a phenomenon in which local error patterns become self-reinforcing. To address this, we propose PURE (Post-hoc Unlocking and REfinement), a training-free inference algorithm for two-phase decoding. PURE profiles confidence dynamics during drafting to identify unstable regions via an instability score ($\Delta_i$), then unlocks them through deterministic window masking and stochastic leftward relaxation. On reasoning benchmarks, PURE substantially improves accuracy when applied to LLaDA-8B-Instruct, including a gain of +12.9 points over the baseline on GSM8K. These gains require only a small refinement budget, yielding a favorable compute-quality trade-off for discrete diffusion decoding."
}