IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models

TL;DR

The paper introduces IESR, a novel modular reasoning framework using MCTS and lightweight LLMs to improve complex Text-to-SQL tasks, achieving state-of-the-art results without fine-tuning.

Contribution

It presents a new reasoning approach combining MCTS with LLMs for Text-to-SQL, emphasizing lightweight models and enhanced reasoning capabilities.

Findings

Achieves state-of-the-art on LogicCat and Archer datasets.

Demonstrates effectiveness of MCTS-based reasoning in Text-to-SQL.

Highlights biases and deficiencies in current code models.

Abstract

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.