mlsanityData to 7 Oct 2026

Balancing Content Size in RAG-Text2SQL System

arXiv 2502.15723 ↗First posted 28 Jan 2025cs.IR cs.AI cs.DBcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have emerged as a promising solution for converting natural language queries into SQL commands, enabling seamless database interaction. However, these Text-to-SQL (Text2SQL) systems face inherent limitations, hallucinations, outdated knowledge, and untraceable reasoning. To address these challenges, the integration of retrieval-augmented generation (RAG) with Text2SQL models has gained traction. RAG serves as a retrieval mechanism, providing essential contextual information, such as table schemas and metadata, to enhance the query generation process. Despite their potential, RAG + Text2SQL systems are susceptible to the quality and size of retrieved documents. While richer document content can improve schema relevance and retrieval accuracy, it also introduces noise, increasing the risk of hallucinations and reducing query fidelity as the prompt size of the Text2SQL model increases. This research investigates the nuanced trade-off between document size and quality, aiming to strike a balance that optimizes system performance. Key thresholds are identified where performance degradation occurs, along with actionable strategies to mitigate these challenges. Additionally, we explore the phenomenon of hallucinations in Text2SQL models, emphasizing the critical role of curated document presentation in minimizing errors. Our findings provide a roadmap for enhancing the robustness of RAG + Text2SQL systems, offering practical insights for real-world applications.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 59 references that are in the map. First posted on arXiv 28 Jan 2025.

Builds on

30 of 59 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  9. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  10. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  11. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  12. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
18 more
  1. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  2. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  3. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  4. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  5. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  6. 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 132
  7. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  8. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  9. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  10. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  11. 2023Trapping LLM Hallucinations Using Tagged Context Promptscited by 34
  12. 2024Text2SQL is Not Enough: Unifying AI and Databases with TAGcited by 34
  13. 2024Estimating the Hallucination Rate of Generative AIcited by 20
  14. 2023Influence of External Information on Large Language Models Mirrors Social Cognitive Patternscited by 16
  15. 2024Question-Analysis Prompting Improves LLM Performance in Reasoning Taskscited by 13
  16. 2024Observations on Building RAG Systems for Technical Documentscited by 8
  17. 2024Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Reportcited by 8
  18. 2024Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systemscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databasescited by 2
  2. 2026TAHOE: Text-to-SQL with Automated Hint Optimization from Experiencecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
  2. 2024Optimizing Query Generation for Enhanced Document Retrieval in RAG
  3. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
  4. 2024Meta Knowledge for Retrieval Augmented Large Language Models
  5. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation System
  6. 2025RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
  7. 2026Progressive Searching for Retrieval in RAG
  8. 2025More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG