@inproceedings{le-etal-2025-lailab,
    title = "{LAIL}ab at {A}rch{EHR}-{QA} 2025: Test-time scaling for evidence selection in grounded question answering from electronic health records",
    author = "Le, Tuan Dung  and
      Duong, Thanh  and
      Haddadan, Shohreh  and
      Jazayeri, Behzad  and
      Manley, Brandon  and
      Thieu, Thanh",
    editor = "Soni, Sarvesh  and
      Demner-Fushman, Dina",
    booktitle = "BioNLP 2025 Shared Tasks",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bionlp-share.9/",
    pages = "75--80",
    ISBN = "979-8-89176-276-3",
    abstract = "This paper presents our approach to the ArchEHR shared task on generating answers to real-world patient questions grounded in evidence from electronic health records (EHRs). We investigate the zero-shot capabilities of general-purpose, domain-agnostic large language models (LLMs) in two key aspects: identifying essential supporting evidence and producing concise, coherent answers. To this aim, we propose a two-stage pipeline: (1) evidence identification via test-time scaling (TTS) and (2) generating the final answer conditioned on selected evidences from the previous stage.Our approach leverages high-temperature sampling to generate multiple outputs during the evidence selection phase. This TTS-based approach effectively explore more potential evidences which results in significant improvement of the factuality score of the answers."
}