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

arXiv: https://arxiv.org/abs/2407.03227 · HTML: https://mlsanity.com/paper/2407.03227/

## 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.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 26 of 26)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://mlsanity.com/paper/2302.05965/) (2023)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [C3: Zero-shot Text-to-SQL with ChatGPT](https://mlsanity.com/paper/2307.07306/) (2023)
- [Structure-Grounded Pretraining for Text-to-SQL](https://mlsanity.com/paper/2010.12773/) (2020)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://mlsanity.com/paper/2303.13547/) (2023)
- [Towards Robustness of Text-to-SQL Models against Synonym Substitution](https://mlsanity.com/paper/2106.01065/) (2021)
- [Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing](https://mlsanity.com/paper/2301.07507/) (2023)
- [Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization](https://mlsanity.com/paper/2109.05157/) (2021)
- [How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings](https://mlsanity.com/paper/2305.11853/) (2023)
- [Does BLEU Score Work for Code Migration?](https://mlsanity.com/paper/1906.04903/) (2019)
- [Skill-Based Few-Shot Selection for In-Context Learning](https://mlsanity.com/paper/2305.14210/) (2023)
- [SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)](https://mlsanity.com/paper/2306.00739/) (2023)
- [Meta-Learning for Domain Generalization in Semantic Parsing](https://mlsanity.com/paper/2010.11988/) (2020)
- [A Pilot Study for Chinese SQL Semantic Parsing](https://mlsanity.com/paper/1909.13293/) (2019)
- [Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain](https://mlsanity.com/paper/2307.05074/) (2023)
- [Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers](https://mlsanity.com/paper/2210.16613/) (2022)

## Built on by (most cited first, 16 of 16)

- [GeAR: Graph-enhanced Agent for Retrieval-augmented Generation](https://mlsanity.com/paper/2412.18431/) (2024)
- [cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree](https://mlsanity.com/paper/2506.15655/) (2025)
- [Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors](https://mlsanity.com/paper/2501.09310/) (2025)
- [ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL](https://mlsanity.com/paper/2505.12768/) (2025)
- [From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Jungle](https://mlsanity.com/paper/2412.12839/) (2024)
- [SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL](https://mlsanity.com/paper/2502.11438/) (2025)
- [DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph](https://mlsanity.com/paper/2505.19956/) (2025)
- [Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities](https://mlsanity.com/paper/2505.23838/) (2025)
- [Exploring Database Normalization Effects on SQL Generation](https://mlsanity.com/paper/2510.01989/) (2025)
- [PExA: Parallel Exploration Agent for Complex Text-to-SQL](https://mlsanity.com/paper/2604.22934/) (2026)
- [Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL](https://mlsanity.com/paper/2605.04719/) (2026)
- [Skeletons Matter: Dynamic Data Augmentation for Text-to-Query](https://mlsanity.com/paper/2511.18934/) (2025)
- [SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback](https://mlsanity.com/paper/2606.01246/) (2026)
- [ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL](https://mlsanity.com/paper/2606.08245/) (2026)
- [Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning](https://mlsanity.com/paper/2606.15598/) (2026)
- [Latent Bridges for Multi-Table Question Answering](https://mlsanity.com/paper/2606.28916/) (2026)

## 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.