@inproceedings{li-etal-2026-dlnlp,
    title = "{DLNLP} at {C}linical{S}kill{QA}: {E}vidence{F}low for Structured Zero-Shot Clinical Keyframe Ordering",
    author = "Li, Kexin  and
      Wang, Zhekun  and
      Wang, Yiran  and
      Zhao, Di",
    editor = "Gupta, Deepak  and
      Demner-Fushman, Dina",
    booktitle = "Proceedings of the {B}io{NLP} 2026 (Shared Tasks)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-2.5/",
    pages = "33--37",
    ISBN = "979-8-89176-435-4",
    abstract = "The ClinSkill QA shared task requires models to recover the temporal order of scrambled clinical keyframes and generate explanations. We propose EvidenceFlow, a structured zero-shot framework based on Qwen2.5-VL that decomposes the task into global overview, local evidence modeling, and ordering decision, with two variants: model-led EvidenceFlow-M and rule-guided EvidenceFlow-R. On the official test set, EvidenceFlow-R achieves better ordering performance, while EvidenceFlow-M produces better explanation quality, revealing a trade-off between ordering stability and rationale generation. EvidenceFlow provides an interpretable zero-shot baseline for clinical keyframe ordering."
}