Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

• URL: http://arxiv.org/abs/2503.23157v2
• Date: Tue, 01 Apr 2025 12:53:16 GMT
• Title: Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL
• Authors: Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun, Xingchen Wan, Hailong Li, Azalia Mirhoseini, Amin Saberi, Sercan "O. Arik,
• Abstract summary: Existing approaches often rely on handcrafted reasoning paths with inductive biases that can limit their overall effectiveness.<n>Motivated by the recent success of reasoning-enhanced models such as OpenAI o1, we propose a novel set of partial rewards tailored specifically for the Text-to- exploration task.<n>We demonstrate that RL-only training with our proposed rewards consistently achieves higher accuracy and superior generalization compared to supervised fine-tuning.
• Score: 13.215512957681185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query formulation. Existing approaches often rely on handcrafted reasoning paths with inductive biases that can limit their overall effectiveness. Motivated by the recent success of reasoning-enhanced models such as DeepSeek R1 and OpenAI o1, which effectively leverage reward-driven self-exploration to enhance reasoning capabilities and generalization, we propose a novel set of partial rewards tailored specifically for the Text-to-SQL task. Our reward set includes schema-linking, AI feedback, n-gram similarity, and syntax check, explicitly designed to address the reward sparsity issue prevalent in reinforcement learning (RL). Leveraging group relative policy optimization (GRPO), our approach explicitly encourages large language models (LLMs) to develop intrinsic reasoning skills necessary for accurate SQL query generation. With models of different sizes, we demonstrate that RL-only training with our proposed rewards consistently achieves higher accuracy and superior generalization compared to supervised fine-tuning (SFT). Remarkably, our RL-trained 14B-parameter model significantly outperforms larger proprietary models, e.g. o3-mini by 4% and Gemini-1.5-Pro-002 by 3% on the BIRD benchmark. These highlight the efficacy of our proposed RL-training framework with partial rewards for enhancing both accuracy and reasoning capabilities in Text-to-SQL tasks.

Related papers

• Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning [66.43194385702297]
  Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL) We propose NEMOTRON-CROSSTHINK, a framework that systematically incorporates multi-domain corpora, including both synthetic and real-world question-answer pairs, into RL training to improve generalization across diverse reasoning tasks.
  arXiv  Detail & Related papers  (2025-04-15T21:37:13Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• 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)
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning [65.2421542320293]
  Reasoning abilities are crucial components of general intelligence.<n>Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks.<n>This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through textbfOutcome textbfREwtextbfArd-based reinforcement textbfLearning for mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-10T18:57:29Z)
• Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation [24.081573908824353]
  First-order logic (FOL) reasoning is pivotal for intelligent systems.<n>Existing benchmarks often rely on extensive human annotation or handcrafted templates.<n>We propose a novel framework called ProverGen that synergizes the generative strengths of Large Language Models with the rigor and precision of symbolic provers.
  arXiv  Detail & Related papers  (2025-02-10T15:31:54Z)
• Reliable Text-to-SQL with Adaptive Abstention [21.07332675929629]
  We present a novel framework that enhances query generation reliability by incorporating abstention and human-in-the-loop mechanisms.<n>We validate our approach through comprehensive experiments on the BIRD benchmark, demonstrating significant improvements in robustness and reliability.
  arXiv  Detail & Related papers  (2025-01-18T19:36:37Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL [0.5735035463793009]
  Large Language Models (LLMs) exhibit impressive problem-solving skills across many tasks, but they still underperform compared to humans in various downstream applications, such as text-to-context. We propose LPE-Leveraging, a novel framework designed to augment LLMs by enabling continual learning without requiring fine-tuning. Our experimental results demonstrate that this continual learning approach yields substantial performance gains.
  arXiv  Detail & Related papers  (2024-11-20T12:03:17Z)
• 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)
• Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework [5.351873055148804]
  Self-training framework generates diverse synthetic data with complex logic. We optimize the procedure using a "Table-Text Manipulator" to handle joint table-text reasoning scenarios. UCTRST achieves above 90% of the supervised model performance on different tasks and domains.
  arXiv  Detail & Related papers  (2022-12-20T09:15:03Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)

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.