# PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency

arXiv: https://arxiv.org/abs/2403.09732 · HTML: https://mlsanity.com/paper/2403.09732/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [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)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://mlsanity.com/paper/2302.05965/) (2023)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [C3: Zero-shot Text-to-SQL with ChatGPT](https://mlsanity.com/paper/2307.07306/) (2023)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Semantic Evaluation for Text-to-SQL with Distilled Test Suites](https://mlsanity.com/paper/2010.02840/) (2020)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought](https://mlsanity.com/paper/2310.17342/) (2023)
- [TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems](https://mlsanity.com/paper/2311.11315/) (2023)
- [Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach](https://mlsanity.com/paper/2311.13884/) (2023)
- [Hybrid Ranking Network for Text-to-SQL](https://mlsanity.com/paper/2008.04759/) (2020)
- [SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Models](https://mlsanity.com/paper/2403.02951/) (2024)
- [SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising](https://mlsanity.com/paper/2105.07911/) (2021)
- [Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function -- with Real Applications in Traffic Domain](https://mlsanity.com/paper/2310.18752/) (2023)

## Built on by (most cited first, 27 of 27)

- [XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL](https://mlsanity.com/paper/2507.04701/) (2025)
- [LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL](https://mlsanity.com/paper/2503.18596/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [ST-Raptor: LLM-Powered Semi-Structured Table Question Answering](https://mlsanity.com/paper/2508.18190/) (2025)
- [MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases](https://mlsanity.com/paper/2410.18406/) (2024)
- [Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks](https://mlsanity.com/paper/2503.05445/) (2025)
- [DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL](https://mlsanity.com/paper/2503.04959/) (2025)
- [LLM+Reasoning+Planning for Supporting Incomplete User Queries in Presence of APIs](https://mlsanity.com/paper/2405.12433/) (2024)
- [DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph](https://mlsanity.com/paper/2505.19956/) (2025)
- [Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval](https://mlsanity.com/paper/2504.09824/) (2025)
- [SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases](https://mlsanity.com/paper/2505.18363/) (2025)
- [Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets](https://mlsanity.com/paper/2407.05674/) (2024)
- [Multi-Turn Interactions for Text-to-SQL with Large Language Models](https://mlsanity.com/paper/2408.11062/) (2024)
- [LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting](https://mlsanity.com/paper/2601.17942/) (2026)
- [ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement](https://mlsanity.com/paper/2603.03742/) (2026)
- [EvoOntology: A Self-Evolving Ontology Layer for Data Agents](https://mlsanity.com/paper/2609.15779/) (2026)
- [Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs](https://mlsanity.com/paper/2504.00048/) (2025)
- [Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task](https://mlsanity.com/paper/2506.11986/) (2025)
- [GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL](https://mlsanity.com/paper/2509.12612/) (2025)
- [ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL](https://mlsanity.com/paper/2511.00985/) (2025)
- [Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL](https://mlsanity.com/paper/2512.17053/) (2025)
- [Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL](https://mlsanity.com/paper/2602.15564/) (2026)
- [Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints](https://mlsanity.com/paper/2511.00772/) (2025)
- [GPG: Generalized Policy Gradient Theorem for Transformer-based Policies](https://mlsanity.com/paper/2512.10365/) (2025)
- [SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback](https://mlsanity.com/paper/2606.01246/) (2026)
- [Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL](https://mlsanity.com/paper/2608.28432/) (2026)
- [LIMIT: Less Is More for Instruction Tuning in Text-to-SQL](https://mlsanity.com/paper/2609.24186/) (2026)

## Abstract (arXiv)

Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM) on in-context learning, achieving significant results. Nevertheless, they face challenges when dealing with verbose database information and complex user intentions. This paper presents a two-stage framework to enhance the performance of current LLM-based natural language to SQL systems. We first introduce a novel prompt representation, called reference-enhanced representation, which includes schema information and randomly sampled cell values from tables to instruct LLMs in generating SQL queries. Then, in the first stage, question-SQL pairs are retrieved as few-shot demonstrations, prompting the LLM to generate a preliminary SQL (PreSQL). After that, the mentioned entities in PreSQL are parsed to conduct schema linking, which can significantly compact the useful information. In the second stage, with the linked schema, we simplify the prompt's schema information and instruct the LLM to produce the final SQL. Finally, as the post-refinement module, we propose using cross-consistency across different LLMs rather than self-consistency within a particular LLM. Our methods achieve new SOTA results on the Spider benchmark, with an execution accuracy of 87.6%.