@inproceedings{chowdhury-etal-2026-fd,
    title = "{FD}-{NL}2{SQL}: Feedback-Driven Clinical {NL}2{SQL} that Improves with Use",
    author = "Chowdhury, Suparno Roy  and
      Anvekar, Tejas  and
      Choudhury, Manan Roy  and
      Khan, Muhammad Ali  and
      Khakwani, Kaneez Zahra Rubab  and
      Sonbol, M Bassam  and
      Riaz, Irbaz Bin  and
      Gupta, Vivek",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.75/",
    pages = "764--773",
    ISBN = "979-8-89176-392-0",
    abstract = "Clinicians exploring oncology trial repositories often need ad-hoc, multi-constraint queries over biomarkers, endpoints, interventions, and time, yet writing SQL requires schema expertise. We demo FD-NL2SQL, a feedback-driven clinical NL2SQL assistant for SQLite-based oncology databases. Given a natural-language question, a schema-aware LLM decomposes it into predicate-level sub-questions, retrieves semantically similar expert-verified NL2SQL exemplars via sentence embeddings, and synthesizes executable SQL conditioned on the decomposition, retrieved exemplars, and schema, with post-processing validity checks. To improve with use, FD-NL2SQL incorporates two update signals: (i) clinician edits of generated SQL are approved and added to the exemplar bank; and (ii) lightweight logic-based SQL augmentation applies a single atomic mutation (e.g., operator or column change), retaining variants only if they return non-empty results. A second LLM generates the corresponding natural-language question and predicate decomposition for accepted variants, automatically expanding the exemplar bank without additional annotation. The demo interface exposes decomposition, retrieval, synthesis, and execution results to support interactive refinement and continuous improvement."
}