@inproceedings{phasook-etal-2025-vereafine,
    title = "{V}e{R}ea{F}ine: Iterative Verification Reasoning Refinement {RAG} for Hallucination-Resistant on Open-Ended Clinical {QA}",
    author = "Phasook, Pakawat  and
      Pitijaroonpong, Rapepong  and
      Kinchagawat, Jiramet  and
      Chinkamol, Amrest  and
      Saengja, Tossaporn  and
      Udomlapsakul, Kiartnarin  and
      Sawatphol, Jitkapat  and
      Ittichaiwong, Piyalitt",
    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.34/",
    pages = "281--288",
    ISBN = "979-8-89176-276-3",
    abstract = "We present VeReaFine, a novel ``Verifier-RAG'' pipeline designed to eliminate hallucinations in open-ended clinical question answering. VeReaFine interleaves three tightly coupled stages{---}retrieval, verification, and generation{---}across up to three iterations. First, a two-stage dense retriever (BM-Retriever-410M {\textrightarrow} BM-Reranker-2B) fetches and ranks top-k biomedical passages; an 8B-parameter MedReason verifier then filters these for direct relevance and identifies missing evidence. When the verifier deems the context insufficient, it formulates a focused ``feedback query'' to retrieve additional passages (bounded to prevent infinite loops). Once a minimal ground-truth context is assembled, a 7B-parameter generator (Qwen2.5-7B-Instruct) drafts an answer purely from that vetted context, and the verifier performs a final check{---}prompting the generator to refine any remaining unsupported claims. By iteratively fetching only missing facts and ensuring every assertion is evidence-backed, VeReaFine achieves monotonic factuality improvements with minimal overhead. On the BioNLP 2025 ClinIQLink ``LLM Lie-Detector'' shared task, our 7B generator augmented with VeReaFine matches or surpasses a 32B medical model on open-ended reasoning metrics, reducing multi-hop inverse step-identification errors by 26{\%}. These findings demonstrate that moderate-size LLMs, when guided by targeted verification loops, can deliver expert-level reliability in clinical QA."
}