mlsanityData to 14 Oct 2026

You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL

arXiv 2409.12172 ↗First posted 18 Sep 2024cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

While significant progress has been made on the text-to-SQL task, recent solutions repeatedly encode the same database schema for every question, resulting in unnecessary high inference cost and often overlooking crucial database knowledge. To address these issues, we propose You Only Read Once (YORO), a novel paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference. YORO significantly reduces the input token length by 66%-98%. Despite its shorter inputs, our empirical results demonstrate YORO's competitive performances with traditional systems on three benchmarks as well as its significant outperformance on large databases. Furthermore, YORO excels in handling questions with challenging value retrievals such as abbreviation.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 18 Sep 2024.

Builds on

23 of 34 references.

References · 23

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2023LIMA: Less Is More for Alignmentcited by 1,100
  7. 2023Teaching Large Language Models to Self-Debugcited by 988
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  10. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  11. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  12. 2023Learning to Compress Prompts with Gist Tokenscited by 390
11 more
  1. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  2. 2023Adapting Language Models to Compress Contextscited by 356
  3. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
  4. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  5. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 106
  6. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  7. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 53
  8. 2023Extending Context Window of Large Language Models via Semantic Compressioncited by 45
  9. 2024SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Modelscited by 32
  10. 2022Importance of Synthesizing High-quality Data for Text-to-SQL Parsingcited by 28
  11. 2023Selective Demonstrations for Cross-domain Text-to-SQLcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 3.

11 papers.

  1. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 91
  2. 2025EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routingcited by 13
  3. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMscited by 11
  4. 2025On Synthetic Data Strategies for Domain-Specific Generative Retrievalcited by 5
  5. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  6. 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answeringcited by 3
  7. 2025HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidancecited by 1
  8. 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Modelscited by 0
  9. 2026Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesiscited by 0
  10. 2026Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scalecited by 0
  11. 2026Bootstrapping Semantic Layer from Execution for Text-to-SQLcited by 0