# SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data

arXiv: https://arxiv.org/abs/2311.02883 · HTML: https://mlsanity.com/paper/2311.02883/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020)
- [Semantic Evaluation for Text-to-SQL with Distilled Test Suites](https://mlsanity.com/paper/2010.02840/) (2020)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://mlsanity.com/paper/2303.13547/) (2023)
- [RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL](https://mlsanity.com/paper/2205.06983/) (2022)
- [Towards Understanding Mixture of Experts in Deep Learning](https://mlsanity.com/paper/2208.02813/) (2022)

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

- [Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL](https://mlsanity.com/paper/2503.23157/) (2025)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [A Survey of Table Reasoning with Large Language Models](https://mlsanity.com/paper/2402.08259/) (2024)
- [SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging](https://mlsanity.com/paper/2408.12733/) (2024)
- [SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models](https://mlsanity.com/paper/2311.09818/) (2023)
- [Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs](https://mlsanity.com/paper/2510.23854/) (2025)
- [SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL](https://mlsanity.com/paper/2601.17699/) (2026)
- [Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities](https://mlsanity.com/paper/2505.23838/) (2025)
- [Ensembling Language Models with Sequential Monte Carlo](https://mlsanity.com/paper/2603.05432/) (2026)
- [Context-Aware SQL Error Correction Using Few-Shot Learning -- A Novel Approach Based on NLQ, Error, and SQL Similarity](https://mlsanity.com/paper/2410.09174/) (2024)
- [Towards Agentic Schema Refinement](https://mlsanity.com/paper/2412.07786/) (2024)
- [MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL](https://mlsanity.com/paper/2608.09588/) (2026)
- [dIR -- Discrete Information Retrieval: Conversational Search over Unstructured (and Structured) Data with Large Language Models](https://mlsanity.com/paper/2312.13264/) (2023)
- [GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models](https://mlsanity.com/paper/2511.04710/) (2025)
- [When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications](https://mlsanity.com/paper/2605.10176/) (2026)
- [ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL](https://mlsanity.com/paper/2606.08245/) (2026)

## Abstract (arXiv)

Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose "SQLPrompt", tailored to improve the few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs). Our methods include innovative prompt design, execution-based consistency decoding strategy which selects the SQL with the most consistent execution outcome among other SQL proposals, and a method that aims to improve performance by diversifying the SQL proposals during consistency selection with different prompt designs ("MixPrompt") and foundation models ("MixLLMs"). We show that SQLPrompt outperforms previous approaches for in-context learning with few labeled data by a large margin, closing the gap with finetuning state-of-the-art with thousands of labeled data.