Data to 7 Oct 2026

DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models

arXiv 2402.01117 ↗First posted 2 Feb 2024cs.CL cs.DB cs.HCcited by 45

Not on the map. Why?

Abstract (arXiv)

Leading models for the text-to-SQL task heavily rely on proprietary Large Language Models (LLMs), posing concerns over data privacy. Closing the performance gap between small open-source models and large proprietary models is crucial to mitigate this reliance. To this end, we introduce a novel two-stage fine-tuning approach that decomposes the task into two simpler tasks. Through comprehensive evaluation on two large cross-domain datasets and two small LLMs, we show that this approach improves execution accuracy by 3 to 7 percent, effectively aligning the performance of open-source models with their proprietary counterparts.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

30 of 37 references.

References · 30

2017Attention Is All You Needcited by 59,932
2022Training language models to follow instructions with human feedbackcited by 15,712
2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
2017Deep reinforcement learning from human preferencescited by 3,846
2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
2014Sequence to Sequence Learning with Neural Networkscited by 2,974
2020Learning to summarize from human feedbackcited by 2,562
2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
2019Fine-Tuning Language Models from Human Preferencescited by 2,124
2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462

18 more

2022LaMDA: Language Models for Dialog Applicationscited by 1,218
2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
2021SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoisingcited by 27
2024Blar-SQL: Faster, Stronger, Smaller NL2SQLcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 15; 2025: 20; 2026: 10.

45 papers.

Sort:

By area:

2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
2024TableRAG: Million-Token Table Understanding with Language Modelscited by 40
2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQLcited by 19
2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 17

33 more

2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 17
2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 16
2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systemscited by 15
2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13
2024Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQLcited by 12
2026Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboardscited by 12
2025Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQLcited by 9
2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
2024DAC: Decomposed Automation Correction for Text-to-SQLcited by 6
2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
2024Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurementcited by 3
2025MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstractioncited by 3
2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
2025Exploring Database Normalization Effects on SQL Generationcited by 2
2025AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generationcited by 2
2024ChipXplore: Natural Language Exploration of Hardware Designs and Librariescited by 1
2025Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Taskcited by 1
2025SQL-Exchange: Transforming SQL Queries Across Domainscited by 1
2025Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoningcited by 1
2025Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Explorationcited by 1
2026NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutionscited by 1
2026Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQLcited by 1
2024LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarioscited by 0
2025Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsingcited by 0
2025Do LLMs Align with My Task? Evaluating Text-to-SQL via Dataset Alignmentcited by 0
2026Dial: A Knowledge-Grounded Dialect-Specific NL2SQL Systemcited by 0
2026An Agentic System for Schema Aware NL2SQL Generationcited by 0
2026SQL Query Engine: A Self-Healing LLM Pipeline for Natural Language to PostgreSQL Translationcited by 0
2026Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderationcited by 0
2026CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking processcited by 0
2026SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQLcited by 0
2026DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generationcited by 0