@inproceedings{roy-roy-2026-towards,
    title = "Towards Unified Factuality Evaluation for Biomedical {QA} and Summarization: Aligning Metrics with Clinical Use-Cases",
    author = "Roy, Mahule  and
      Roy, Subhas",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-1.2/",
    pages = "15--19",
    ISBN = "979-8-89176-434-7",
    abstract = "Large language models achieve strong performance on biomedical question answering and summarization benchmarks, yet traditional evaluation metrics often fail to detect clinically significant factual errors. We introduce a unified evaluation framework that combines reference-based measures with evidence-grounded factuality verification to assess biomedical text generation. Evaluating four open-source models across three benchmarks (BioASQ, PubMedQA, MedLFQA), we find that 13.4?24.7{\%} of generated claims are contradicted and 23?41{\%} are unsupported, despite high lexical overlap scores. Our proposed Fact-Aligned Score (FAS) correlates strongly with claim-level verifiability (rho=0.68), substantially outperforming ROUGE-L (rho=0.41). We release an open-source toolkit with model outputs and analysis scripts to support reproducible factuality evaluation and safer deployment of biomedical LLMs."
}