Papers by Zhihui Shao

1 papers
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.

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