Text-to-SQL

Ask about this topic

Overview

Text-to-SQL studies how to turn natural-language questions into database queries that retrieve the intended information. Systems link questions to tables, columns, and values, then generate SQL using language models, structured intermediate plans, retrieval, or schema-aware semantic metadata. Common approaches add query decomposition, execution feedback, verification, and iterative repair; training methods include fine-tuning on curated or synthetic examples and reinforcement learning with execution-based rewards. Benchmarks such as Spider and BIRD test execution accuracy, but real deployments also expose challenges in large or changing schemas, ambiguity, multiple SQL dialects, and balancing reliability against cost and latency.

Latest papers

CardsList

173 papers24 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

  1. MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL

    Aug 10, 2026Beiyu Xu, Zhenyu Wu, Jiaoyan Chen +1Schema LinkingText-to-SQL

    University of Manchester Faculty of Science and Engineering Department of Computer Science

  2. SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL

    Aug 10, 2026Geonho Lee, Min-Soo KimLLM Self-RefinementText-to-SQL

    Korea Advanced Institute of Science and Technology Republic of Korea

  3. Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline

    Aug 10, 2026Morris LeeLLM Answer VerificationLLM Agent Evaluation

    Independent Researcher

  4. Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

    Aug 8, 2026Mike HelwigSelective PredictionText-to-SQL

    Independent Researcher USA

  5. From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL

    Aug 7, 2026Jiaqian Wang, Yutao Qi, Wenjin Hou +2LLM MemoryText-to-SQL

    Xidian University · Xidian University Xi’an, Shaanxi, China · Shanghai Jiao Tong University +1

  6. Causal Episodic Memory for Feedback-Driven Agent Repair

    Aug 6, 2026Khang Nhat Hoang Vo, Tam Minh Chu, Anh Trac Duc Dinh +2LLM Self-CorrectionLLM Agent Memory

    Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Ho Chi Minh City, Vietnam

  7. Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks

    Aug 4, 2026Shunfan Zheng, Dongsheng Shi, Yue Li +3LLM EvaluationText-to-SQL

    1East China Normal University · 2Hasso Plattner Institute/University of Potsdam

  8. BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL

    Aug 3, 2026Chong Peng, Pin Qian, Su Wang +2Cost-Aware InferenceText-to-SQL

    Microsoft · Carnegie Mellon University · Georgia Institute of Technology

  9. AttnLink: Turning Attention into Schema Links for Text-to-SQL

    Aug 1, 2026Jinwang Song, Tao Liu, Haowen Zheng +3Schema LinkingText-to-SQL

  10. SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning

    Aug 1, 2026Tao Liu, Tao Feng, Xiangheng Li +9Reinforcement LearningText-to-SQL

    Zhejiang University, College of Artificial Intelligence · Zhengzhou University, School of Computer Science of Artificial Intelligence · Byte Dance

  11. How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

    Jul 28, 2026Mahendra Singh Rathor, Anagheem AzzamMemory-Efficient Fine-TuningSmall Language Models

    Independent Researcher · Jaipur, India · Hamburg, Germany

  12. SAFAARI: Schema-Aware Framework for Accelerated Advertiser Response Intelligence

    Jul 27, 2026Bhanu Teja Rangaraju, Chandan KumarMulti-Agent LLM SystemsCustomer Support Automation

    Amazon, Seattle, USA.

  13. Benchmarking Text-to-SQL under Role-Based Access Control

    Jul 24, 2026Yang Fei, Yangfan Jiang, Yin Yang +1Text-to-SQLSynthetic Benchmark Generation

    National University of Singapore · Hamad Bin Khalifa University

  14. Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval

    Jul 14, 2026Qingcheng Zeng, Puxuan Yu, Aman Mehta +2Schema LinkingText-to-SQL

    Northwestern University · Snowflake Inc.

  15. Policy-Conditioned Constrained Decoding for Column-Level Access Control in Text-to-SQL

    Jul 14, 2026Ryoto Miyamoto, Xin Fan, Hayato YamanaPrivacy Leakage in Language ModelsText-to-SQL

    Waseda University

  16. The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions

    Jul 12, 2026Filip Klubicka, Vasudevan Nedumpozhimana, Sneha Rautmare +3Text-to-SQL

    ADAPT Research Centre Trinity College Dublin Dublin, Ireland · Huawei Ireland Research Centre Dublin, Ireland

  17. GRID: Grammar-Railed Decoding for Enterprise SQL Generation

    Jul 11, 2026Mohsen ArjmandiLLM GuardrailsText-to-SQL

    evolutionID GmbH

  18. SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation

    Jul 9, 2026Wangyu Wu, Xiaojian Lin, Rong Fu +4Small Language ModelsText-to-SQL

    The University of Liverpool · Microsoft · Tsinghua University +4

  19. What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study

    Jul 7, 2026Robert RichardsonLLM Answer VerificationSelective Prediction

    Affiliation

  20. Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows

    Jul 7, 2026Tianyang Liu, Canwen Xu, Fangyu Lei +6Text-to-SQLRelational Databases

    1UC San Diego · *Work done during Tianyang Liu’s internship at Snowflake. · 2Snowflake AI Research +1

  21. Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL

    Jul 4, 2026Yaron Anavi, Mor Aisenberg, Nadav Nesher +2LLM Inference EfficiencyLLM Inference

    GIGASPACES

  22. Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL

    Jul 4, 2026Hanqing Wang, Yongdong Chi, Jian Yang +4LLM SecurityText-to-SQL

    Shanghai University of Finance and Economics · Beihang University · Deepexi Technology Co. Ltd. +1

  23. STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Data

    Jul 3, 2026Yi Zhang, Farhad Nooralahzadeh, Jonathan Fürst +4Spatiotemporal ReasoningText-to-SQL

    Zurich University of Applied Sciences · National Oberservatory of Athens

  24. Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents

    Jun 30, 2026Utsav Garg, Sungjin Hong, Jason Jung +6Multilingual Language ModelsLLM Fine-Tuning

    1Cohere

  25. A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases

    Jun 30, 2026Ha Jeong Kim, Saksonita Khoeurn, Ye Ji YoonText-to-SQLRelational Databases

    DAQUV Corp. Seoul, Republic of Korea · Dept. of Management Information Systems Chungbuk National University BigDataLabs, Co., Ltd. Cheongju, Republic of Korea

  26. Test-Time Verification for Text-to-SQL via Outcome Reward Models

    Jun 29, 2026Mattia Tritto, Giuseppe Farano, Dario Di Palma +4Reward ModelingLLM Answer Verification

    Polytechnic University of Bari, Bari, Italy · IBM T.J. Watson Research Center, Yorktown Heights, NY, USA

  27. How far do on-premises open LLMs get on Text-to-SQL? A cross-family size and technique frontier on BIRD

    Jun 29, 2026Vladimir BeskorovainyiLLM Self-CorrectionLLM Evaluation

    Besk Tech | Moscow Institute of Physics and Technology (MIPT)

  28. Database Context Compression for Text-to-SQL on Real-World Large Databases

    Jun 26, 2026Jingwen Liu, Weibin Liao, Xin Gao +2Text-to-SQLRelational Databases

    1National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · 3Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +1

  29. Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics

    Jun 23, 2026Adarsh Agrawal, Shashank IndukuriTable RetrievalText-to-SQL

  30. SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration

    Jun 22, 2026Yizhang Zhu, Zhangyang Peng, Boyan Li +1Text-to-SQLRL for Tool Use

    HKUST(GZ) Guangzhou, China