LLCE-SQL: Data-Efficient Text-to-SQL Training via Logic-Linking Driven Collaborative Evolution
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 4247-4257
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62471252)
- Qinglan Project of Jiangsu
This publication has 28 references indexed in Scilit:
- Text2sql-Flow: a Robust Sql-Aware Data Augmentation Framework for Text-To-Sql2026
- Next-Generation Database Interfaces: A Survey of LLM-Based Text-to-SQLIEEE Transactions on Knowledge and Data Engineering, 2025
- OmniSQL: Synthesizing High-Quality Text-to-SQL Data at ScaleProceedings of the VLDB Endowment, 2025
- FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis2024
- Text-to-SQL Empowered by Large Language Models: A Benchmark EvaluationProceedings of the VLDB Endowment, 2024
- ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL SystemsProceedings of the VLDB Endowment, 2023
- RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLProceedings of the AAAI Conference on Artificial Intelligence, 2023
- UMLS-based data augmentation for natural language processing of clinical research literatureJournal of the American Medical Informatics Association, 2021
- Text-to-SQL Generation for Question Answering on Electronic Medical Records2020
- On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries2020