mlsanityData to 7 Oct 2026

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

arXiv 2402.10663 ↗First posted 16 Feb 2024cs.CLcited by 10

Not on the map. Why?

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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

25 of 39 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  9. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  10. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  11. 2022Binding Language Models in Symbolic Languagescited by 224
  12. 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
13 more
  1. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  2. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136
  3. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  4. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  5. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 69
  6. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  7. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
  8. 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategiescited by 44
  9. 2023Selective Demonstrations for Cross-domain Text-to-SQLcited by 21
  10. 2024Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentationcited by 17
  11. 2024Using LLM to select the right SQL Query from candidatescited by 12
  12. 2021Less is more: Selecting informative and diverse subsets with balancing constraintscited by 5
  13. 2023The Re-Label Method For Data-Centric Machine Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 1.

10 papers.

  1. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  2. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  3. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  4. 2024In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Taskscited by 3
  5. 2024Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs without Real Data Replaycited by 3
  6. 2025Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrievalcited by 3
  7. 2025Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusionscited by 1
  8. 2025ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQLcited by 1
  9. 2026PExA: Parallel Exploration Agent for Complex Text-to-SQLcited by 1
  10. 2025Skeletons Matter: Dynamic Data Augmentation for Text-to-Querycited by 0