@inproceedings{srikanth-etal-2025-sqlspace,
    title = "{SQLS}pace: A Representation Space for Text-to-{SQL} to Discover and Mitigate Robustness Gaps",
    author = "Srikanth, Neha  and
      Bursztyn, Victor  and
      Mathur, Puneet  and
      Nenkova, Ani",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.81/",
    doi = "10.18653/v1/2025.findings-emnlp.81",
    pages = "1533--1559",
    ISBN = "979-8-89176-335-7",
    abstract = "We introduce SQLSpace, a human-interpretable, generalizable, compact representation for text-to-SQL examples derived with minimal human intervention. We demonstrate the utility of these representations in evaluation with three use cases: (i) closely comparing and contrasting the composition of popular NL2SQL benchmarks to identify unique dimensions of examples they evaluate, (ii) understanding model performance at a granular level beyond overall accuracy scores, and (iii) improving model performance through targeted query rewriting based on learned correctness estimation. We show that SQLSpace enables analysis that would be difficult with raw examples alone: it reveals compositional differences between benchmarks, exposes performance patterns obscured by accuracy alone, and supports modeling of query success."
}