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

arXiv: https://arxiv.org/abs/2310.18742 · HTML: https://mlsanity.com/paper/2310.18742/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2023.

## Built on by (most cited first, 11 of 11)

- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries](https://mlsanity.com/paper/2406.19073/) (2024)
- [BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions](https://mlsanity.com/paper/2510.05318/) (2025)
- [SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL](https://mlsanity.com/paper/2506.04494/) (2025)
- [StatBot.Swiss: Bilingual Open Data Exploration in Natural Language](https://mlsanity.com/paper/2406.03170/) (2024)
- [Query and Conquer: Execution-Guided SQL Generation](https://mlsanity.com/paper/2503.24364/) (2025)
- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [Towards Green AI: Current status and future research](https://mlsanity.com/paper/2407.10237/) (2024)
- [Towards Agentic Schema Refinement](https://mlsanity.com/paper/2412.07786/) (2024)
- [Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence](https://mlsanity.com/paper/2507.10281/) (2025)
- [Bootstrapping Semantic Layer from Execution for Text-to-SQL](https://mlsanity.com/paper/2606.05634/) (2026)

## Abstract (arXiv)

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 We examine how documentation, originally made to help humans to disambiguate data, can help GPT-4 with Text-to-SQL tasks.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%.