# Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL

arXiv: https://arxiv.org/abs/2402.10663 · HTML: https://mlsanity.com/paper/2402.10663/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 16 Feb 2024.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (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)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [Diverse Demonstrations Improve In-context Compositional Generalization](https://mlsanity.com/paper/2212.06800/) (2022)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [In-context Learning with Retrieved Demonstrations for Language Models: A Survey](https://mlsanity.com/paper/2401.11624/) (2024)
- [ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought](https://mlsanity.com/paper/2310.17342/) (2023)
- [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)
- [Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies](https://mlsanity.com/paper/2305.12586/) (2023)
- [Selective Demonstrations for Cross-domain Text-to-SQL](https://mlsanity.com/paper/2310.06302/) (2023)
- [Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation](https://mlsanity.com/paper/2401.06643/) (2024)
- [Using LLM to select the right SQL Query from candidates](https://mlsanity.com/paper/2401.02115/) (2024)
- [Less is more: Selecting informative and diverse subsets with balancing constraints](https://mlsanity.com/paper/2104.12835/) (2021)
- [The Re-Label Method For Data-Centric Machine Learning](https://mlsanity.com/paper/2302.04391/) (2023)

## Built on by (most cited first, 10 of 10)

- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [A Survey on Employing Large Language Models for Text-to-SQL Tasks](https://mlsanity.com/paper/2407.15186/) (2024)
- [Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities](https://mlsanity.com/paper/2505.23838/) (2025)
- [In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks](https://mlsanity.com/paper/2410.01548/) (2024)
- [Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs without Real Data Replay](https://mlsanity.com/paper/2412.07246/) (2024)
- [Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval](https://mlsanity.com/paper/2504.09824/) (2025)
- [Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions](https://mlsanity.com/paper/2506.23146/) (2025)
- [ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL](https://mlsanity.com/paper/2511.00985/) (2025)
- [PExA: Parallel Exploration Agent for Complex Text-to-SQL](https://mlsanity.com/paper/2604.22934/) (2026)
- [Skeletons Matter: Dynamic Data Augmentation for Text-to-Query](https://mlsanity.com/paper/2511.18934/) (2025)

## Abstract (arXiv)

Currently, the in-context learning method based on large language models (LLMs) has become the mainstream of text-to-SQL research. Previous works have discussed how to select demonstrations related to the user question from a human-labeled demonstration pool. However, human labeling suffers from the limitations of insufficient diversity and high labeling overhead. Therefore, in this paper, we discuss how to measure and improve the diversity of the demonstrations for text-to-SQL. We present a metric to measure the diversity of the demonstrations and analyze the insufficient of the existing labeled data by experiments. Based on the above discovery, we propose fusing iteratively for demonstrations (Fused) to build a high-diversity demonstration pool through human-free multiple-iteration synthesis, improving diversity and lowering label cost. Our method achieves an average improvement of 3.2% and 5.0% with and without human labeling on several mainstream datasets, which proves the effectiveness of Fused.