ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects

• URL: http://arxiv.org/abs/2505.17231v1
• Date: Thu, 22 May 2025 19:13:34 GMT
• Title: ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
• Authors: Jipeng Zhang, Haolin Yang, Kehao Miao, Ruiyuan Zhang, Renjie Pi, Jiahui Gao, Xiaofang Zhou,
• Abstract summary: This work introduces Exe, a text-to-guided framework with execution-driven, agentic bootstrapping.<n>We show that Exe bridges the dialect gap in text-to-guided learning, achieving average improvements of 15.2%, 10.38%, and 4.49% over GPT-4o on, and Oracle, respectively.
• Score: 24.450818792474216
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent text-to-SQL models have achieved strong performance, but their effectiveness remains largely confined to SQLite due to dataset limitations. However, real-world applications require SQL generation across multiple dialects with varying syntax and specialized features, which remains a challenge for current models. The main obstacle in building a dialect-aware model lies in acquiring high-quality dialect-specific data. Data generated purely through static prompting - without validating SQLs via execution - tends to be noisy and unreliable. Moreover, the lack of real execution environments in the training loop prevents models from grounding their predictions in executable semantics, limiting generalization despite surface-level improvements from data filtering. This work introduces ExeSQL, a text-to-SQL framework with execution-driven, agentic bootstrapping. The method consists of iterative query generation, execution-based filtering (e.g., rejection sampling), and preference-based training, enabling the model to adapt to new SQL dialects through verifiable, feedback-guided learning. Experiments show that ExeSQL bridges the dialect gap in text-to-SQL, achieving average improvements of 15.2%, 10.38%, and 4.49% over GPT-4o on PostgreSQL, MySQL, and Oracle, respectively, across multiple datasets of varying difficulty.

Related papers

• RetrySQL: text-to-SQL training with retry data for self-correcting query generation [1.6707278580444538]
  We introduce Retry, a new approach to training text-to-generation models.<n>We demonstrate that retry steps yield an improvement of up to 4 percentage points in both overall and challenging execution accuracy metrics.
  arXiv  Detail & Related papers  (2025-07-03T11:00:49Z)
• Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation [26.834687657847454]
  Text-to-sql models are increasingly adopted in real-world applications.<n> deploying such models in the real world often requires adapting them to the highly specialized database schemas used in specific applications.<n>We find that existing text-to-sql models experience significant performance drops when applied to new schemas.<n> Continuously obtaining high-quality text-to-sql data for evolving schemas is prohibitively expensive in real-world scenarios.
  arXiv  Detail & Related papers  (2025-02-21T22:32:35Z)
• MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation [10.205010004198757]
  Text-to-generation enables non-experts to interact with databases via natural language.<n>Recent advances on large closed-source models like GPT-4 present challenges in accessibility, privacy, and latency.<n>We focus on developing small, efficient, and open-source text-to-generation models.
  arXiv  Detail & Related papers  (2024-10-16T18:03:24Z)
• SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging [30.306023265985658]
  We introduce a framework for generating high-quality synthetic training data for any dialect. We propose a novel Mixture-of-Experts (MoE) that leverages the shared knowledge across dialects.
  arXiv  Detail & Related papers  (2024-08-22T20:50:48Z)
• SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data [54.69489315952524]
  "Prompt" is designed to improve the few-shot prompting capabilities of Text-to-LLMs. "Prompt" outperforms previous approaches for in-context learning with few labeled data by a large margin. We show that emphPrompt outperforms previous approaches for in-context learning with few labeled data by a large margin.
  arXiv  Detail & Related papers  (2023-11-06T05:24:06Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)
• Wav2SQL: Direct Generalizable Speech-To-SQL Parsing [55.10009651476589]
  Speech-to-Spider (S2Spider) aims to convert spoken questions intosql queries given databases. We propose the first direct speech-to-speaker parsing model Wav2 which avoids error compounding across cascaded systems. Experimental results demonstrate that Wav2 avoids error compounding and achieves state-of-the-art results by up to 2.5% accuracy improvement over the baseline.
  arXiv  Detail & Related papers  (2023-05-21T19:26:46Z)
• A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions [102.8606542189429]
  The goal of text-to-corpora parsing is to convert a natural language (NL) question to its corresponding structured query language () based on the evidences provided by databases. Deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output query.
  arXiv  Detail & Related papers  (2022-08-29T14:24:13Z)
• Weakly Supervised Text-to-SQL Parsing through Question Decomposition [53.22128541030441]
  We take advantage of the recently proposed question meaning representation called QDMR. Given questions, their QDMR structures (annotated by non-experts or automatically predicted) and the answers, we are able to automatically synthesizesql queries. Our results show that the weakly supervised models perform competitively with those trained on NL- benchmark data.
  arXiv  Detail & Related papers  (2021-12-12T20:02:42Z)
• Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker [1.049360126069332]
  We propose a novel discnative re-ranker to improve the performance of generative text-to-rimi models. We analyze relative strengths of the text-to-rimi and re-ranker models for optimal performance. We demonstrate the effectiveness of the re-ranker by applying it to two state-of-the-art text-to-rimi models.
  arXiv  Detail & Related papers  (2020-02-03T04:52:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.