IESR:基于MCTS的高效模块化推理用于文本到SQL with大型语言模型
IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models
AI总结：
IESR提出一种基于MCTS的高效模块化推理框架，用于文本到SQL任务，通过信息增强和结构化推理提升复杂查询处理能力。
摘要：
文本到SQL是一种关键的自然语言处理任务，将自然语言问题映射到SQL查询，使用户能够直观地与基于网页的数据库进行交互。尽管当前方法在BIRD和Spider等基准测试中表现良好，但它们在复杂推理、领域知识和假设查询方面存在困难，并且在企业部署中仍然成本高昂。为了解决这些问题，我们提出了一种名为IESR（信息增强的结构化推理）的框架，适用于轻量级大型语言模型：（i）利用LLM进行关键信息理解和模式链接，并将数学计算和SQL生成解耦；（ii）集成了基于蒙特卡洛树搜索（MCTS）的多路径推理机制，采用多数投票；（iii）引入了具有判别模型的轨迹一致性验证模块，以确保准确性和一致性。实验结果表明，IESR在复杂推理基准LogicCat（24.28 EX）和Archer数据集（37.28 EX）上使用仅紧凑的轻量模型实现了最先进的性能，无需微调。此外，我们的分析揭示了当前编码模型在物理知识、数学计算和常识推理方面存在显著的偏见和缺陷，突显了未来研究的重要方向。我们已发布代码至https://github.com/Ffunkytao/IESR-SLM。
英文摘要：
Text-to-SQL is a key natural language processing task that maps natural language questions to SQL queries, enabling intuitive interaction with web-based databases. Although current methods perform well on benchmarks like BIRD and Spider, they struggle with complex reasoning, domain knowledge, and hypothetical queries, and remain costly in enterprise deployment. To address these issues, we propose a framework named IESR(Information Enhanced Structured Reasoning) for lightweight large language models: (i) leverages LLMs for key information understanding and schema linking, and decoupling mathematical computation and SQL generation, (ii) integrates a multi-path reasoning mechanism based on Monte Carlo Tree Search (MCTS) with majority voting, and (iii) introduces a trajectory consistency verification module with a discriminator model to ensure accuracy and consistency. Experimental results demonstrate that IESR achieves state-of-the-art performance on the complex reasoning benchmark LogicCat (24.28 EX) and the Archer dataset (37.28 EX) using only compact lightweight models without fine-tuning. Furthermore, our analysis reveals that current coder models exhibit notable biases and deficiencies in physical knowledge, mathematical computation, and common-sense reasoning, highlighting important directions for future research. We released code at https://github.com/Ffunkytao/IESR-SLM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
