@inproceedings{cai-etal-2025-columbo,
    title = "Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models",
    author = "Cai, Ting  and
      Sheen, Stephen  and
      Doan, AnHai",
    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/name-variant-enfa-fane/2025.findings-emnlp.1348/",
    doi = "10.18653/v1/2025.findings-emnlp.1348",
    pages = "24774--24792",
    ISBN = "979-8-89176-335-7",
    abstract = "Expanding the abbreviated column names of tables, such as ``esal'' to ``employee salary'', is critical for many downstream NLP tasks for tabular data, such as NL2SQL, table QA, and keyword search. This problem arises in enterprises, domain sciences, government agencies, and more. In this paper, we make three contributions that significantly advance the state of the art. First, we show that the synthetic public data used by prior work has major limitations, and we introduce four new datasets in enterprise/science domains, with real-world abbreviations. Second, we show that accuracy measures used by prior work seriously undercount correct expansions, and we propose new synonym-aware measures that capture accuracy much more accurately. Finally, we develop Columbo, a powerful LLM-based solution that exploits context, rules, chain-of-thought reasoning, and token-level analysis. Extensive experiments show that Columbo significantly outperforms NameGuess, the current most advanced solution, by 4-29{\%}, over five datasets. Columbo has been used in production on EDI, a major data lake for environmental sciences."
}