Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models

Wenqi Pei, Hailing Xu, Henry Hengyuan Zhao, CHEN Han, Zining Zhang, Shizheng Hou, Luo Pingyi, Bingsheng He

Track: long paper (up to 9 pages)

Keywords: Small Language Models, Text-to-SQL, NL2SQL

Abstract: Natural Language to SQL (NL2SQL) has seen significant advancements with large language models (LLMs). However, these models often depend on closed-source systems and high computational resources, posing challenges in data privacy and deployment. In contrast, small language models (SLMs) struggle with NL2SQL tasks, exhibiting poor performance and incompatibility with existing frameworks. To address these issues, we introduce Feather-SQL, a new lightweight frame- work tailored for SLMs. Feather-SQL improves SQL executability and accuracy through 1) schema pruning and linking, 2) multi-path and multi-candidate gen- eration. Additionally, we introduce the 1+1 Model Collaboration Paradigm, which pairs a strong general-purpose chat model with a fine-tuned SQL special- ist, combining strong analytical reasoning with high-precision SQL generation. Experimental results on BIRD demonstrate that Feather-SQL improves NL2SQL performance on SLMs, with around 10% boost for models without fine-tuning. The proposed paradigm raises the accuracy ceiling of SLMs to 54.76%, highlighting its effectiveness.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 22