Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL
On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval
Abstract (arXiv)
The current state-of-the-art (SOTA) for automated text-to-SQL still falls well short of expert human performance as measured by execution accuracy (EX) on the BIRD-SQL benchmark. The most accurate methods are also slow and expensive. To advance the SOTA for text-to-SQL while reducing cost and improving speed, we explore the combination of low-cost fine tuning, novel methods for diverse retrieval-augmented generation (RAG) and new input and output formats that help large language models (LLMs) achieve higher EX. We introduce two new methods, Dubo-SQL v1 and v2. Dubo-SQL v1 sets a new record for EX on the holdout test set of BIRD-SQL. Dubo-SQL v2 achieves even higher performance on the BIRD-SQL dev set. Dubo-SQL v1 relies on LLMs from OpenAI, but uses the low-cost GPT-3.5 Turbo while exceeding the performance of the next-best model using OpenAI, which instead uses the more expensive GPT-4. Dubo-SQL v1 exceeds the performance of the next-best model using GPT-3.5 by over 20%. Dubo-SQL v2 uses GPT-4 Turbo and RAG in place of fine tuning to push EX higher.
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 14 references that are in the map. First posted on arXiv 19 Apr 2024.
Builds on
9 of 14 references.
References · 9
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2023Large Language Modelscited by 780
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
Built on by
Citing papers per year: 2024: 3; 2025: 6; 2026: 3.
12 papers.
- 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
- 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
- 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 53
- 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
- 2025Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotationcited by 6
- 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
- 2026PExA: Parallel Exploration Agent for Complex Text-to-SQLcited by 1
- 2024The Role of Accuracy and Validation Effectiveness in Conversational Business Analyticscited by 0
- 2025Meta-aware Learning in text-to-SQL Large Language Modelcited by 0
- 2025DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Modelcited by 0
- 2026CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domaincited by 0
- 2026Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMscited by 0
- 2026Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs12 Sep 2026
- 2026PExA: Parallel Exploration Agent for Complex Text-to-SQL24 Apr 2026
- 2026CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain5 Mar 2026
- 2025DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Model27 Oct 2025
- 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities28 May 2025
- 2025Meta-aware Learning in text-to-SQL Large Language Model25 May 2025
- 2025Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation21 Feb 2025
- 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment19 Feb 2025
- 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation18 Feb 2025
- 2024The Role of Accuracy and Validation Effectiveness in Conversational Business Analytics18 Nov 2024
- 2024A Survey on Employing Large Language Models for Text-to-SQL Tasks21 Jul 2024
- 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL12 Jun 2024
Similar, not cited
Close in wording, no citation either way
- 2026CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
- 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
- 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
- 2024Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning
- 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
- 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation
- 2024SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL
- 2025Auto prompt sql: a resource-efficient architecture for text-to-sql translation in constrained environments