mlsanityData to 7 Oct 2026

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm

arXiv 2402.10671 ↗First posted 16 Feb 2024cs.CLcited by 31

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing, while extensive case studies reveal that the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition. Specifically, the information determination module for eliminating redundant information and the brand-new prompt structure based on problem classification greatly enhance the model's attention. Additionally, the inclusion of self-correction and active learning modules greatly expands the problem-solving scope of LLMs, hence improving the upper limit of LLM-based approaches. Extensive experiments conducted on three datasets demonstrate that our approach outperforms other methods by a significant margin. About 2-3 percentage point improvements compared to the existing baseline on the Spider Dev, Spider-Realistic, and Bird Dev datasets and new SOTA results on the Spider Test dataset are achieved. Our code is available on GitHub: urlhttps://github.com/FlyingFeather/DEA-SQL.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 32 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

21 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought26 Oct

Other references · 20

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  4. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  5. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  6. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  7. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  8. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  9. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  10. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  11. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  12. 2018Improving Text-to-SQL Evaluation Methodologycited by 133
8 more
  1. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  2. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  3. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  4. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  5. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  6. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  7. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
  8. 2023Selective Demonstrations for Cross-domain Text-to-SQLcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 13; 2026: 9.

31 papers.

Sort:

By area:

  1. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  2. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  3. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  4. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  5. 2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQLcited by 22
  6. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
  7. 2025SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQLcited by 15
  8. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  9. 2024SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaborationcited by 10
  10. 2025BASE-SQL: A powerful open source Text-To-SQL baseline approachcited by 9
  11. 2024PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQLcited by 7
  12. 2024DAC: Decomposed Automation Correction for Text-to-SQLcited by 6
19 more
  1. 2024Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarioscited by 4
  2. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  3. 2024Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answeringcited by 3
  4. 2026Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQLcited by 3
  5. 2025MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translationcited by 2
  6. 2025RetrySQL: text-to-SQL training with retry data for self-correcting query generationcited by 2
  7. 2025Large Language Models Transform Organic Synthesis From Reaction Prediction to Automationcited by 1
  8. 2025ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQLcited by 1
  9. 2026NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutionscited by 1
  10. 2025SPORTSQL: An Interactive System for Real-Time Sports Reasoning and Visualizationcited by 0
  11. 2025Agentic generative AI for media content discovery at the national football leaguecited by 0
  12. 2025DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Modelcited by 0
  13. 2026Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Methodcited by 0
  14. 2026Residual Skill Optimization for Text-to-SQL Ensemblescited by 0
  15. 2026Enhancing LLM Medical Coding with Structured External Knowledgecited by 0
  16. 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedbackcited by 0
  17. 2026ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQLcited by 0
  18. 2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQLcited by 0
  19. 2026Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL
  2. 2024Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models
  3. 2024Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL
  4. 2024CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions
  5. 2025Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing
  6. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
  7. 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency
  8. 2024Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and Refinement