mlsanityData to 14 Oct 2026

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

arXiv 2503.17811 ↗First posted 22 Mar 2025cs.CL cs.AI cs.DBcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 22 Mar 2025.

Builds on

32 of 52 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 723
  7. 2024Yi: Open Foundation Models by 01.AIcited by 719
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  10. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  11. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  12. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
20 more
  1. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  2. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  3. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  4. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
  5. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  6. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  7. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  8. 2023Understanding Catastrophic Forgetting in Language Models via Implicit Inferencecited by 144
  9. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 138
  10. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  11. 2024Granite Code Models: A Family of Open Foundation Models for Code Intelligencecited by 117
  12. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  13. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  14. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 50
  15. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
  16. 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34
  17. 2024Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Treecited by 20
  18. 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 19
  19. 2019IRNet: A General Purpose Deep Residual Regression Framework for Materials Discoverycited by 8
  20. 2023A Multilingual Translator to SQL with Database Schema Pruning to Improve Self-Attentioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ROSE: An Intent-Centered Evaluation Metric for NL2SQLcited by 0
  2. 2026BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotationscited by 0