ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback
Text-to-SQL demands precise reasoning to convert natural language questions into structured queries. While large language models (LLMs) excel in many reasoning tasks, their ability to leverage Chain-of-Thought (CoT) reasoning for text-to-SQL remains underexplored. We identify critical limitations: zero-shot CoT offers minimal gains, and Direct Preference Optimization (DPO) applied without CoT yields marginal improvements. We propose ExCoT, a novel framework that iteratively optimizes open-source LLMs by combining CoT reasoning with off-policy and on-policy DPO, relying solely on execution accuracy as feedback. This approach eliminates the need for reward models or human-annotated preferences. Our experimental results demonstrate significant performance gains: ExCoT improves execution accuracy on BIRD dev set from 57.37% to 68.51% and on Spider test set from 78.81% to 86.59% for LLaMA-3 70B, with Qwen-2.5-Coder demonstrating similar improvements. Our best model achieves state-of-the-art performance in the single-model setting on both BIRD and Spider datasets, notably achieving 68.53% on the BIRD test set.
Code (1)
Tasks
Text to SQLText-To-SQLMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EXCOTATE: An Add-on to MMAX2 for Inspection and Exchange of Annotated Data
ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL
In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc sig…
Text to SQLText-To-SQLMTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, …
Reinforcement LearningRecursive Harness Self-Improvement
Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models. This motivates harness-in-the-loop learning: …
Continual LearningAnticipatory Planning for Multimodal AI Agents
Recent advances in multimodal agents have improved computer-use interaction and tool-usage, yet most existing systems remain reactive, optimizing actions in isolation without reasoning about future states or long-term go…
Reinforcement Learning