REFORMER: A ChatGPT-Driven Data Synthesis Framework Elevating Text-to-SQL Models
Not on the map. Why?
Abstract (arXiv)
The existing Text-to-SQL models suffer from a shortage of training data, inhibiting their ability to fully facilitate the applications of SQL queries in new domains. To address this challenge, various data synthesis techniques have been employed to generate more diverse and higher quality data. In this paper, we propose REFORMER, a framework that leverages ChatGPT's prowess without the need for additional training, to facilitate the synthesis of (question, SQL query) pairs tailored to new domains. Our data augmentation approach is based on a "retrieve-and-edit" method, where we generate new questions by filling masked question using explanation of SQL queries with the help of ChatGPT. Furthermore, we demonstrate that cycle consistency remains a valuable method of validation when applied appropriately. Our experimental results show that REFORMER consistently outperforms previous data augmentation methods. To further investigate the power of ChatGPT and create a general data augmentation method, we also generate the new data by paraphrasing the question in the dataset and by paraphrasing the description of a new SQL query that is generated by ChatGPT as well. Our results affirm that paraphrasing questions generated by ChatGPT help augment the original data.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 31 references that are in the map. First posted on arXiv 6 Apr 2025.
Builds on
26 of 31 references.
References · 26
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
- 2019Language Models as Knowledge Bases?cited by 1,936
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
- 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
- 2021Template-Based Named Entity Recognition Using BARTcited by 153
14 more
- 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
- 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
- 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
- 2023ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systemscited by 45
- 2021Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Datacited by 43
- 2021Learning to Synthesize Data for Semantic Parsingcited by 41
- 2021ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parsercited by 35
- 2021Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsingcited by 33
- 2018Question Generation from SQL Queries Improves Neural Semantic Parsingcited by 29
- 2022Importance of Synthesizing High-quality Data for Text-to-SQL Parsingcited by 28
- 2021Logic-Consistency Text Generation from Semantic Parsescited by 23
- 2021ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learningcited by 18
- 2021Hierarchical Neural Data Synthesis for Semantic Parsingcited by 11
- 2022Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parserscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.