Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL

Abstract

Text-to-SQL allows experts to use databases without in-depth knowledge of them. However, real-world tasks have both query and data ambiguities. Most works on Text-to-SQL focused on query ambiguities and designed chat interfaces for experts to provide clarifications. In contrast, the data management community has long studied data ambiguities, but mainly addresses error detection and correction, rather than documenting them for disambiguation in data tasks. This work delves into these data ambiguities in real-world datasets. We have identified prevalent data ambiguities of value consistency, data coverage, and data granularity that affect tasks. We examine how documentation, originally made to help humans to disambiguate data, can help GPT-4 with Text-to-SQL tasks. By offering documentation on these, we found GPT-4's performance improved by $28.9$%.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Huang et al. "Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL." NeurIPS 2023 Workshops: TRL, 2023.

Markdown

[Huang et al. "Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL." NeurIPS 2023 Workshops: TRL, 2023.](https://mlanthology.org/neuripsw/2023/huang2023neuripsw-data/)

BibTeX

@inproceedings{huang2023neuripsw-data,
  title     = {{Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL}},
  author    = {Huang, Zezhou and Damalapati, Pavan Kalyan and Wu, Eugene},
  booktitle = {NeurIPS 2023 Workshops: TRL},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/huang2023neuripsw-data/}
}