SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning

• URL: http://arxiv.org/abs/2509.03937v2
• Date: Sat, 11 Oct 2025 08:01:48 GMT
• Title: SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning
• Authors: Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han,
• Abstract summary: Self-play fine-tuning (SPIN) can transform a weak large language model (LLM) into a strong one through competitive interactions.<n>We propose a new self-play fine-tuning method tailored for the Text-to- task, called SPFT-tuning.<n>During the self-play fine-tuning phase, we propose an error-driven loss method that incentivizes incorrect outputs from the opponent model.
• Score: 8.501743260277324
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Despite the significant advancements of self-play fine-tuning (SPIN), which can transform a weak large language model (LLM) into a strong one through competitive interactions between models of varying capabilities, it still faces challenges in the Text-to-SQL task. SPIN does not generate new information, and the large number of correct SQL queries produced by the opponent model during self-play reduces the main model's ability to generate accurate SQL queries. To address this challenge, we propose a new self-play fine-tuning method tailored for the Text-to-SQL task, called SPFT-SQL. Prior to self-play, we introduce a verification-based iterative fine-tuning approach, which synthesizes high-quality fine-tuning data iteratively based on the database schema and validation feedback to enhance model performance, while building a model base with varying capabilities. During the self-play fine-tuning phase, we propose an error-driven loss method that incentivizes incorrect outputs from the opponent model, enabling the main model to distinguish between correct SQL and erroneous SQL generated by the opponent model, thereby improving its ability to generate correct SQL. Extensive experiments and in-depth analyses on six open-source LLMs and five widely used benchmarks demonstrate that our approach outperforms existing state-of-the-art (SOTA) methods.

Related papers

• ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement [57.98138819417949]
  We propose ErrorLLM, a framework that explicitly models text-to- querying.<n>We show that ErrorLLM achieves the most significant improvements over backbone initial generation.<n>ErrorLLM addresses both sides by high detection F1 score while maintaining refinement effectiveness.
  arXiv  Detail & Related papers  (2026-03-04T05:27:20Z)
• SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL [20.49395306069103]
  We introduce a multi-turn reinforcement learning (RL) agentic framework for Text-to-one generation.<n>Rather than producing a query in one shot, SQL-Trail interacts with the database environment and uses execution feedback to iteratively refine its predictions.<n>Our approach centers on two key ideas: (i) an adaptive turn-budget allocation mechanism that scales the agent's interaction depth to match question difficulty, and (ii) a composite reward panel that jointly incentivizessql correctness and efficient exploration.
  arXiv  Detail & Related papers  (2026-01-25T05:16:52Z)
• 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)
• 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)
• Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement [1.392448435105643]
  Text-to-s enables non-expert users to effortlessly retrieve desired information from databases using natural language queries. Current state-of-the-art (SOTA) models like GPT4 and T5 have shown impressive performance on large-scale benchmarks like BIRD. This paper proposed a novel approach that only needs SQL Quality to enhance Text-to-s performance.
  arXiv  Detail & Related papers  (2024-10-02T17:21:51Z)
• DAC: Decomposed Automation Correction for Text-to-SQL [51.48239006107272]
  We introduce De Automation Correction (DAC), which corrects text-to-composed by decomposing entity linking and skeleton parsing. We show that our method improves performance by $3.7%$ on average of Spider, Bird, and KaggleDBQA compared with the baseline method.
  arXiv  Detail & Related papers  (2024-08-16T14:43:15Z)
• 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)
• TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring [11.78795632771211]
  We introduce a novel benchmark designed to evaluate text-to- reliability as a model's ability to correctly handle any type of input question. We evaluate existing methods using a novel penalty-based scoring metric with two modeling approaches.
  arXiv  Detail & Related papers  (2024-03-23T16:12:52Z)
• 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)
• SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers [61.48159785138462]
  This paper aims to improve the performance of text-to-dependence by exploring the intrinsic uncertainties in the neural network based approaches (called SUN) Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms competitors and achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-09-14T06:27:51Z)
• IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation [61.09660709356527]
  We propose a database schema interaction graph encoder to utilize historicalal information of database schema items. We evaluate our model on the benchmark SParC and Co datasets.
  arXiv  Detail & Related papers  (2020-11-11T12:56:21Z)

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.