Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search (2502.17248v2)

Published 24 Feb 2025 in cs.DB

Abstract: Text-to-SQL, which enables natural language interaction with databases, serves as a pivotal method across diverse industries. With new, more powerful LLMs emerging every few months, fine-tuning has become incredibly costly, labor-intensive, and error-prone. As an alternative, zero-shot Text-to-SQL, which leverages the growing knowledge and reasoning capabilities encoded in LLMs without task-specific fine-tuning, presents a promising and more challenging direction. To address this challenge, we propose Alpha-SQL, a novel approach that leverages a Monte Carlo Tree Search (MCTS) framework to iteratively infer SQL construction actions based on partial reasoning states. To enhance the framework's reasoning capabilities, we introduce LLM-as-Action-Model to dynamically generate SQL construction actions during the MCTS process, steering the search toward more promising SQL queries. Moreover, Alpha-SQL employs a self-supervised reward function to evaluate the quality of candidate SQL queries, ensuring more accurate and efficient query generation. Experimental results show that Alpha-SQL achieves 69.7% execution accuracy on the BIRD development set, using a 32B open-source LLM without fine-tuning. Alpha-SQL outperforms the best previous zero-shot approach based on GPT-4o by 2.5% on the BIRD development set.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Boyan Li (17 papers)
  2. Jiayi Zhang (159 papers)
  3. Ju Fan (26 papers)
  4. Yanwei Xu (10 papers)
  5. Chong Chen (122 papers)
  6. Nan Tang (63 papers)
  7. Yuyu Luo (41 papers)

Summary

We haven't generated a summary for this paper yet.