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

Pei Wenqi, hailingxu, Hengyuan Zhao, Shizheng Hou, CHEN Han, Zining Zhang, Pingyi Luo, Bingsheng He

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models: 13 upvotes on Hugging Face Daily Papers, #14 of 39 papers on 2025-03-25. Day-by-day upvote history.

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 framework tailored for SLMs. Feather-SQL improves SQL executability and accuracy through 1) schema pruning and linking, 2) multi-path and multi-candidate generation. Additionally, we introduce the 1+1 Model Collaboration Paradigm, which pairs a strong general-purpose chat model with a fine-tuned SQL specialist, 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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.