# Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL

arXiv: https://arxiv.org/abs/2212.08902 · HTML: https://mlsanity.com/paper/2212.08902/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 17 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [A General Framework for Uncertainty Estimation in Deep Learning](https://mlsanity.com/paper/1907.06890/) (2019)
- [On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries](https://mlsanity.com/paper/2010.11246/) (2020)
- [Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study](https://mlsanity.com/paper/1910.05389/) (2019)
- [Confidence Modeling for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04604/) (2018)
- [Design Challenges and Misconceptions in Neural Sequence Labeling](https://mlsanity.com/paper/1806.04470/) (2018)
- [Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing](https://mlsanity.com/paper/2109.10540/) (2021)
- [Photon: A Robust Cross-Domain Text-to-SQL System](https://mlsanity.com/paper/2007.15280/) (2020)
- ["What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQL](https://mlsanity.com/paper/2011.04151/) (2020)
- [Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categories](https://mlsanity.com/paper/1804.08460/) (2018)
- [ColloQL: Robust Cross-Domain Text-to-SQL Over Search Queries](https://mlsanity.com/paper/2010.09927/) (2020)

## Built on by (most cited first, 6 of 6)

- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)
- [Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions](https://mlsanity.com/paper/2212.10189/) (2022)
- [Uncovering and Categorizing Social Biases in Text-to-SQL](https://mlsanity.com/paper/2305.16253/) (2023)
- [LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries](https://mlsanity.com/paper/2601.10398/) (2026)
- [Datrics Text2SQL: A Framework for Natural Language to SQL Query Generation](https://mlsanity.com/paper/2506.12234/) (2025)
- [TrustDABench: Benchmarking Reliability and Robustness of LLMs for Structured Data Analysis](https://mlsanity.com/paper/2608.24145/) (2026)

## Abstract (arXiv)

The task of text-to-SQL aims to convert a natural language question into its corresponding SQL query within the context of relational tables. Existing text-to-SQL parsers generate a "plausible" SQL query for an arbitrary user question, thereby failing to correctly handle problematic user questions. To formalize this problem, we conduct a preliminary study on the observed ambiguous and unanswerable cases in text-to-SQL and summarize them into 6 feature categories. Correspondingly, we identify the causes behind each category and propose requirements for handling ambiguous and unanswerable questions. Following this study, we propose a simple yet effective counterfactual example generation approach that automatically produces ambiguous and unanswerable text-to-SQL examples. Furthermore, we propose a weakly supervised DTE (Detecting-Then-Explaining) model for error detection, localization, and explanation. Experimental results show that our model achieves the best result on both real-world examples and generated examples compared with various baselines. We release our data and code at: hrefhttps://github.com/wbbeyourself/DTEhttps://github.com/wbbeyourself/DTE.