Papers with Text-to-SQL framework

4 papers
Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks (2026.acl-demo)

Copied to clipboard

Challenge: Existing methods are designed for specific settings, each with its own set of challenges.
Approach: They propose a unified, modular, and extensive Text-to-SQL framework . it proposes a universal execution paradigm and a multi-actor collaboration mechanism .
Outcome: Squrve proposes a unified, modular, and extensive Text-to-SQL framework . the framework outperforms existing methods on widely adopted benchmarks .
ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)

Copied to clipboard

Challenge: Current Text-to-SQL reasoning models lack integrated execution feedback during generation.
Approach: They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback.
Outcome: The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale.
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.
R3-SQL: Ranking Reward and Resampling for Text-to-SQL (2026.findings-acl)

Copied to clipboard

Challenge: Existing rankers assign inconsistent scores to functionally equivalent SQL queries . ranking cannot recover when the correct SQL is absent from the pool.
Approach: They propose a Text-to-SQL framework that rewards ranking and resampling . it first groups candidates by execution result and ranks groups for consistency .
Outcome: The proposed framework achieves 75.03 execution accuracy on BIRD-dev, a new state of the art among methods using models with disclosed sizes.

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