EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis

• URL: http://arxiv.org/abs/2601.04875v1
• Date: Thu, 08 Jan 2026 12:19:50 GMT
• Title: EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis
• Authors: Xuanguang Pan, Chongyang Tao, Jiayuan Bai, Jianling Gao, Zhengwei Tao, Xiansheng Zhou, Gavin Cheung, Shuai Ma,
• Abstract summary: Evol is a structure-aware data synthesis framework that evolves queries into richer and more semantically diverse forms.<n>A 7B model outperforms one trained on the much larger Syn dataset using only 1/18 of the data.
• Score: 25.689983072200047
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training effective Text-to-SQL models remains challenging due to the scarcity of high-quality, diverse, and structurally complex datasets. Existing methods either rely on limited human-annotated corpora, or synthesize datasets directly by simply prompting LLMs without explicit control over SQL structures, often resulting in limited structural diversity and complexity. To address this, we introduce EvolSQL, a structure-aware data synthesis framework that evolves SQL queries from seed data into richer and more semantically diverse forms. EvolSQL starts with an exploratory Query-SQL expansion to broaden question diversity and improve schema coverage, and then applies an adaptive directional evolution strategy using six atomic transformation operators derived from the SQL Abstract Syntax Tree to progressively increase query complexity across relational, predicate, aggregation, and nesting dimensions. An execution-grounded SQL refinement module and schema-aware deduplication further ensure the creation of high-quality, structurally diverse mapping pairs. Experimental results show that a 7B model fine-tuned on our data outperforms one trained on the much larger SynSQL dataset using only 1/18 of the data.

Related papers

• SQaLe: A Large Text-to-SQL Corpus Grounded in Real Schemas [2.905751301655124]
  Key bottleneck for developing text-to-hugging models is lack of large-scale datasets with sufficient schema and query complexity, domain coverage, and task diversity.<n>We introduce SQaLe: a large-scale semi-synthetic text-to-hugging dataset built on 135,875 relational database schemas expanded from a collection of real-world schemas,Pile.<n>SQaLe captures realistic schema size variability, diverse query patterns, and natural language ambiguity while maintaining execution validity.
  arXiv  Detail & Related papers  (2025-12-16T09:15:10Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation [2.0799061948689306]
  SING-a is a fully automated two-stage framework for generating high-quality, high-coverage synthetic Text-to-data.<n>SING-LM is a family of compact language models fine-tuned on the synthetic data.
  arXiv  Detail & Related papers  (2025-09-30T02:14:49Z)
• RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models [83.6013616017646]
  RelDiff is a novel diffusion generative model that synthesizes complete relational databases by explicitly modeling their foreign key graph structure.<n>RelDiff consistently outperforms prior methods in producing realistic and coherent synthetic relational databases.
  arXiv  Detail & Related papers  (2025-05-31T21:01:02Z)
• UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification [50.59009084277447]
  We introduce UNJOIN, a framework that decouples the retrieval of schema elements from logic generation.<n>In the first stage, we merge the column names of all tables in the database into a single-table representation by prefixing each column with its table name.<n>In the second stage, the query is generated on this simplified schema and mapped back to the original schema by reconstructing JOINs, UNIONs, and relational logic.
  arXiv  Detail & Related papers  (2025-05-23T17:28:43Z)
• Synthesizing Text-to-SQL Data from Weak and Strong LLMs [68.69270834311259]
  The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to- tasks. We introduce a synthetic data approach that combines data produced by larger, more powerful models with error information data generated by smaller, not well-aligned models.
  arXiv  Detail & Related papers  (2024-08-06T15:40:32Z)
• CHESS: Contextual Harnessing for Efficient SQL Synthesis [1.9506402593665235]
  We introduce CHESS, a framework for efficient and scalable text-to- queries. It comprises four specialized agents, each targeting one of the aforementioned challenges. Our framework offers features that adapt to various deployment constraints.
  arXiv  Detail & Related papers  (2024-05-27T01:54:16Z)
• Structure Guided Large Language Model for SQL Generation [14.079764882536077]
  We propose a novel structure-aware text-to- query and framework(SGU)<n>SGU-aware text-to- query and framework(SGU) consistently outperforms state-of-the-art text-to-models.
  arXiv  Detail & Related papers  (2024-02-19T09:07:59Z)
• DBCopilot: Natural Language Querying over Massive Databases via Schema Routing [47.009638761948466]
  We present DBCopilot, a framework that addresses challenges by employing a compact and flexible copilot model for routing over massive databases.<n>This framework utilizes a single lightweight differentiable search index to construct semantic mappings for massive database schemata, and navigates natural language questions to their target databases and tables in a relation joint retrieval manner.
  arXiv  Detail & Related papers  (2023-12-06T12:37:28Z)
• 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)
• Importance of Synthesizing High-quality Data for Text-to-SQL Parsing [71.02856634369174]
  State-of-the-art text-to-weighted algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We propose a novel framework that incorporates key relationships from schema, imposes strong typing, and schema-weighted column sampling.
  arXiv  Detail & Related papers  (2022-12-17T02:53:21Z)

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.