mlsanityData to 14 Oct 2026

Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning

arXiv 2407.03227 ↗First posted 3 Jul 2024cs.CL cs.AI cs.DBcited by 16

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

We focus on Text-to-SQL semantic parsing from the perspective of retrieval-augmented generation. Motivated by challenges related to the size of commercial database schemata and the deployability of business intelligence solutions, we propose ASTReS that dynamically retrieves input database information and uses abstract syntax trees to select few-shot examples for in-context learning. Furthermore, we investigate the extent to which an in-parallel semantic parser can be leveraged for generating approximated versions of the expected SQL queries, to support our retrieval. We take this approach to the extreme--we adapt a model consisting of less than 500M parameters, to act as an extremely efficient approximator, enhancing it with the ability to process schemata in a parallelised manner. We apply ASTReS to monolingual and cross-lingual benchmarks for semantic parsing, showing improvements over state-of-the-art baselines. Comprehensive experiments highlight the contribution of modules involved in this retrieval-augmented generation setting, revealing interesting directions for future work.

Key facts. Cited by 16 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 26 of its 36 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

26 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain11 Jul

Other references · 25

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  4. 2023Teaching Large Language Models to Self-Debugcited by 988
  5. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  6. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 479
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  10. 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Modelscited by 246
  11. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  12. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
13 more
  1. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  2. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  3. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 119
  4. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  5. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  6. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  7. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 58
  8. 2019Does BLEU Score Work for Code Migration?cited by 49
  9. 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
  10. 2023SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)cited by 42
  11. 2020Meta-Learning for Domain Generalization in Semantic Parsingcited by 41
  12. 2019A Pilot Study for Chinese SQL Semantic Parsingcited by 33
  13. 2022Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parserscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 8; 2026: 6.

16 papers.

Sort:

By area:

  1. 2024GeAR: Graph-enhanced Agent for Retrieval-augmented Generationcited by 17
  2. 2025cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Treecited by 17
  3. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  4. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  5. 2024From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Junglecited by 4
  6. 2025SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQLcited by 4
  7. 2025DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graphcited by 4
  8. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  9. 2025Exploring Database Normalization Effects on SQL Generationcited by 2
  10. 2026PExA: Parallel Exploration Agent for Complex Text-to-SQLcited by 1
  11. 2026Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQLcited by 1
  12. 2025Skeletons Matter: Dynamic Data Augmentation for Text-to-Querycited by 0
4 more
  1. 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedbackcited by 0
  2. 2026ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQLcited by 0
  3. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuningcited by 0
  4. 2026Latent Bridges for Multi-Table Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Datrics Text2SQL: A Framework for Natural Language to SQL Query Generation
  2. 2024Multi-Turn Interactions for Text-to-SQL with Large Language Models
  3. 2026CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
  4. 2025CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description
  5. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
  6. 2025RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
  7. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
  8. 2019Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study