mlsanityData to 7 Oct 2026

Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers

arXiv 2210.16613 ↗First posted 29 Oct 2022cs.CL cs.AI cs.LGcited by 7

On the map: Synthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping

Abstract (arXiv)

Text-to-SQL parsers typically struggle with databases unseen during the train time. Adapting parsers to new databases is a challenging problem due to the lack of natural language queries in the new schemas. We present ReFill, a framework for synthesizing high-quality and textually diverse parallel datasets for adapting a Text-to-SQL parser to a target schema. ReFill learns to retrieve-and-edit text queries from the existing schemas and transfers them to the target schema. We show that retrieving diverse existing text, masking their schema-specific tokens, and refilling with tokens relevant to the target schema, leads to significantly more diverse text queries than achievable by standard SQL-to-Text generation methods. Through experiments spanning multiple databases, we demonstrate that fine-tuning parsers on datasets synthesized using ReFill consistently outperforms the prior data-augmentation methods.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Synthetic reasoning data and bootstrapping, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 31 of its 45 references that are in the map. First posted on arXiv 29 Oct 2022.

Builds on

31 of 45 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2018Hierarchical Neural Story Generationcited by 1,182
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  8. 2018Self-Attention with Relative Position Representationscited by 1,112
  9. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  10. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  11. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  12. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
19 more
  1. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  2. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  3. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  4. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  5. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  6. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  7. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  8. 2021Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Datacited by 43
  9. 2020Optimizing Deeper Transformers on Small Datasetscited by 41
  10. 2021Learning to Synthesize Data for Semantic Parsingcited by 41
  11. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  12. 2021Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsingcited by 32
  13. 2018Question Generation from SQL Queries Improves Neural Semantic Parsingcited by 29
  14. 2019Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsingcited by 24
  15. 2021Logic-Consistency Text Generation from Semantic Parsescited by 23
  16. 2020DuoRAT: Towards Simpler Text-to-SQL Modelscited by 17
  17. 2019Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databasescited by 15
  18. 2021RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsingcited by 15
  19. 2021Hierarchical Neural Data Synthesis for Semantic Parsingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 3; 2026: 2.

7 papers.

  1. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  2. 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 31
  3. 2024Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruningcited by 16
  4. 2025A survey of diversity quantification in natural language processing: The why, what, where and howcited by 4
  5. 2025REFORMER: A ChatGPT-Driven Data Synthesis Framework Elevating Text-to-SQL Modelscited by 1
  6. 2026A Diversity Diet for a Healthier Model: A Case Study of French ModernBERTcited by 0
  7. 2026Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis
  2. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
  3. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
  4. 2026LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
  5. 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation
  6. 2026BIRDTurk: Adaptation of the BIRD Text-to-SQL Dataset to Turkish
  7. 2025RetrySQL: text-to-SQL training with retry data for self-correcting query generation
  8. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs