Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward

• URL: http://arxiv.org/abs/2505.12380v2
• Date: Fri, 27 Jun 2025 12:45:33 GMT
• Title: Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward
• Authors: Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen,
• Abstract summary: Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to- tasks.<n>Existing methods often rely on execution-based or LLM-based Bradley-Terry reward models.<n>We propose a novel Text-to- RL fine-tuning framework named Graph-Reward-Reward, which employs the GMNScore outcome reward model.
• Score: 15.448159172903138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to-SQL tasks. However, existing methods often rely on execution-based or LLM-based Bradley-Terry reward models. The former suffers from high execution latency caused by repeated database calls, whereas the latter imposes substantial GPU memory overhead, both of which significantly hinder the efficiency and scalability of RL pipelines. To this end, we propose a novel Text-to-SQL RL fine-tuning framework named Graph-Reward-SQL, which employs the GMNScore outcome reward model. We leverage SQL graph representations to provide accurate reward signals while significantly reducing inference time and GPU memory usage. Building on this foundation, we further introduce StepRTM, a stepwise reward model that provides intermediate supervision over Common Table Expression (CTE) subqueries. This encourages both functional correctness and structural clarity of SQL. Extensive comparative and ablation experiments on standard benchmarks, including Spider and BIRD, demonstrate that our method consistently outperforms existing reward models.

Related papers

• CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation [1.169202600932732]
  We introduce Cogni-R1-Zero, a reinforcement learning (RL) framework and model.<n>We use a lightweight reward signal based on execution correctness and format-tag compliance.<n>Our method achieves state-of-the-art execution accuracy on Text2 benchmark.<n>To support further research in efficient and interpretable Text-to-code modeling, we release two curated datasets.
  arXiv  Detail & Related papers  (2025-07-08T14:17:07Z)
• STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing [2.8977258426533115]
  We propose STRuCT-LLM, a unified framework for training large language models (LLMs)<n>Our approach jointly optimize Text-to-aware and Text-to-Cypher tasks using reinforcement learning (RL) combined with Chain-Thought supervision (CoT)
  arXiv  Detail & Related papers  (2025-06-15T22:40:36Z)
• Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL [35.21185734929167]
  We present Arctic-Text2-R1, a reinforcement learning (RL) framework and model family designed to generate accurate, executablesql.<n>Our approach avoids curated intermediate supervision and complex reward shaping, promoting stable training and alignment with the end task.<n> Notably, our 7B model outperforms prior 70B-class systems, highlighting the framework's scalability and efficiency.
  arXiv  Detail & Related papers  (2025-05-22T23:33:47Z)
• Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning [0.12289361708127876]
  This work reframes the Text-to-the-task as a pathway for teaching large language models (LLMs) to reason over and manipulate data.<n>We propose a two-stage framework that teaches a model how to traverse, filter, and aggregate table fields.<n> Empirically, our approach achieves substantial gains on reasoning-intensive datasets such as BIRD and CRT-QA.
  arXiv  Detail & Related papers  (2025-04-23T19:02:04Z)
• STaR-SQL: Self-Taught Reasoner for Text-to-SQL [20.719165038519744]
  "chain-of-thought" rationales have proven effective for improving the performance of large language models on complex reasoning tasks.<n>Applying such techniques to structured tasks, such as text-to-driven, remains largely unexplored.<n>In this paper, we introduce Self-Taughter for text-to-driven (STaR-), a novel approach that reframes query generation as a reasoning process.<n> Experimental results on the challenging Spider benchmark demonstrate that STaR- significantly improves text-to-performance, achieving an execution accuracy of 86.6%.<n>These findings underscore the potential of reasoning-augmented training for
  arXiv  Detail & Related papers  (2025-02-19T08:58:44Z)
• MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search [1.166711394125328]
  Text-to-OTA is a fundamental yet challenging task in the NLP area.<n>We propose MCTS-OTA, a novel framework that uses Monte Carlo Tree Search.<n>We propose a token-level prefixcache mechanism that stores prior information during iterations.
  arXiv  Detail & Related papers  (2025-01-28T00:52:23Z)
• Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL [83.99974309930072]
  Knowledge distillation (KD) is a common approach, which aims to distill the larger teacher model into a smaller student model. We propose to improve the KD with Imperfect Data, namely KID, which effectively boosts the performance without introducing much training budget. KID can not only achieve consistent and significant performance gains across all model types and sizes, but also effectively improve the training efficiency.
  arXiv  Detail & Related papers  (2024-10-15T07:51:00Z)
• RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL [48.516004807486745]
  Large language models (LLMs) with in-context learning have significantly improved the performance of text-to- task. We propose RB-, a novel retrieval-based framework for in-context prompt engineering. Experiment results demonstrate that our model achieves better performance than several competitive baselines on public datasets BIRD and Spider.
  arXiv  Detail & Related papers  (2024-07-11T08:19:58Z)
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [76.76046657162306]
  Large language models (LLMs) have emerged as a new paradigm for Text-to- task. Large language models (LLMs) have emerged as a new paradigm for Text-to- task.
  arXiv  Detail & Related papers  (2023-08-29T14:59:54Z)
• 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)
• Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing [66.55478402233399]
  We propose a framework to elicit relational structures via a probing procedure based on Poincar'e distance metric. Compared with commonly-used rule-based methods for schema linking, we found that probing relations can robustly capture semantic correspondences. Our framework sets new state-of-the-art performance on three benchmarks.
  arXiv  Detail & Related papers  (2022-06-28T14:05:25Z)
• Improving Text-to-SQL with Schema Dependency Learning [22.07452161565993]
  Execution-guided decoding relies on database execution, which slows down the inference process and is unsatisfactory for many real-world applications. We present the Dependency guided multi-task Text-to-task model (SD) to guide the network to effectively capture the interactions between questions and schemas.
  arXiv  Detail & Related papers  (2021-03-07T16:56:56Z)
• 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.