Papers with Text-to-SQL tasks

7 papers
PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are powerful tools for Text-to-SQL tasks . SQL solutions have a relatively fixed pattern, allowing for categorical thinking .
Approach: They propose that query group partitioning allows LLMs to focus on learning the thought processes specific to a single problem type, thus enhancing their reasoning abilities across diverse difficulty levels and problem categories.
Outcome: The proposed model outperforms state-of-the-art models on the Spider and BIRD datasets.
Enhancing Text-to-SQL with Question Classification and Multi-Agent Collaboration (2025.findings-naacl)

Copied to clipboard

Challenge: Existing research focuses on the optimization of prompts and improvements in workflow, with few studies delving into the exploration of the questions.
Approach: They propose a text-to-SQL framework based on question classification and multi-agent collaboration (QCMA-Sql) they employ multiple cross-attention mechanisms to train a schema selector to classify questions and select the most suitable database schema.
Outcome: The proposed framework outperforms state-of-the-art methods on the Spider dataset and achieves 87.4% execution accuracy.
Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)

Copied to clipboard

Challenge: Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases.
Approach: They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram.
Outcome: The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries.
Enhancing SQL Table Acquisition with Reverse Engineering for Text-to-SQL (2025.findings-emnlp)

Copied to clipboard

Challenge: Text-to-SQL oriented table acquisition suffers from heterogeneous semantic gap.
Approach: They propose a Reverse Engineering based table acquisition approach that reversely generates potentially-matched questions conditioned on table schemas instead of forward table search using queries.
Outcome: The proposed approach achieves competitive performance on two benchmarks, including SpiderUnion and BirdUnion.
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach: They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome: The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.
Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL translation (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) understand textual description to generate code in zero-shot scenarios, but there is a possibility that this ability may be influenced by having seen target textual descriptions and the related code.
Approach: They propose a method to detect Data Contamination in Large Language Models (LLMs) and analyze their results on Termite and Spider Datasets to investigate their method.
Outcome: The proposed method detects data contamination in GPTs and analyzes its performance on unfamiliar datasets.
Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been successful in Text-to-SQL tasks, but their deployment in real-world environments is hindered by latent reliability issues.
Approach: They propose a framework to autonomously uncover latent failure patterns in LLM-based Text-to-SQL generation.
Outcome: The proposed framework uncovers a substantial number of failure cases on state-of-the-art open-source LLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations