{"total":87,"rows":[{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688,"area":null},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164,"area":null},{"id":"2406.08426","title":"Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL","created":"2024-06-12","cited_by_count":120,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87,"area":null},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67,"area":null},{"id":"2408.05109","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","created":"2024-08-09","cited_by_count":56,"area":null},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53,"area":null},{"id":"2208.10099","title":"Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect","created":"2022-08-22","cited_by_count":47,"area":null},{"id":"2305.14210","title":"Skill-Based Few-Shot Selection for In-Context Learning","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2301.07695","title":"EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2306.04743","title":"ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems","created":"2023-06-07","cited_by_count":45,"area":null},{"id":"2409.02038","title":"BEAVER: An Enterprise Benchmark for Text-to-SQL","created":"2024-09-03","cited_by_count":42,"area":null},{"id":"2401.10506","title":"FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis","created":"2024-01-19","cited_by_count":36,"area":null},{"id":"2406.19073","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2310.13659","title":"Benchmarking and Improving Text-to-SQL Generation under Ambiguity","created":"2023-10-20","cited_by_count":34,"area":null},{"id":"2402.12243","title":"Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark","created":"2024-02-19","cited_by_count":34,"area":null},{"id":"2305.12820","title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","created":"2023-05-22","cited_by_count":32,"area":null},{"id":"2403.02951","title":"SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Models","created":"2024-03-05","cited_by_count":32,"area":null},{"id":"2501.12372","title":"Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2404.09889","title":"Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval","created":"2024-04-15","cited_by_count":27,"area":null},{"id":"2311.07509","title":"A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases","created":"2023-11-13","cited_by_count":25,"area":null},{"id":"2306.08891","title":"Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation","created":"2023-06-15","cited_by_count":24,"area":null},{"id":"2209.04994","title":"Knowledge Base Question Answering: A Semantic Parsing Perspective","created":"2022-09-12","cited_by_count":22,"area":null},{"id":"2310.06302","title":"Selective Demonstrations for Cross-domain Text-to-SQL","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2410.11076","title":"PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries","created":"2024-10-14","cited_by_count":19,"area":null},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2403.15879","title":"TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring","created":"2024-03-23","cited_by_count":17,"area":null},{"id":"2112.06311","title":"Weakly Supervised Text-to-SQL Parsing through Question Decomposition","created":"2021-12-12","cited_by_count":15,"area":null},{"id":"2305.16265","title":"UNITE: A Unified Benchmark for Text-to-SQL Evaluation","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2411.05521","title":"SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark","created":"2024-11-08","cited_by_count":14,"area":null},{"id":"2402.12554","title":"Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2305.13683","title":"Error Detection for Text-to-SQL Semantic Parsing","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2402.08349","title":"Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries","created":"2024-02-13","cited_by_count":12,"area":null},{"id":"2305.01598","title":"From Words to Code: Harnessing Data for Program Synthesis from Natural Language","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2409.12172","title":"You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL","created":"2024-09-18","cited_by_count":11,"area":null},{"id":"2501.09527","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","created":"2025-01-16","cited_by_count":11,"area":null},{"id":"2310.00749","title":"SEED: Domain-Specific Data Curation With Large Language Models","created":"2023-10-01","cited_by_count":10,"area":null},{"id":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2402.10663","title":"Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL","created":"2024-02-16","cited_by_count":10,"area":null},{"id":"2406.07860","title":"BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain","created":"2024-06-12","cited_by_count":10,"area":null},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2308.02582","title":"Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Prompting","created":"2023-08-01","cited_by_count":8,"area":null},{"id":"2310.11634","title":"MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations","created":"2023-10-18","cited_by_count":7,"area":null},{"id":"2311.01862","title":"$R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL","created":"2023-11-03","cited_by_count":7,"area":null},{"id":"2407.14568","title":"SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy","created":"2024-07-19","cited_by_count":7,"area":null},{"id":"2406.03170","title":"StatBot.Swiss: Bilingual Open Data Exploration in Natural Language","created":"2024-06-05","cited_by_count":6,"area":null},{"id":"2408.08779","title":"DAC: Decomposed Automation Correction for Text-to-SQL","created":"2024-08-16","cited_by_count":6,"area":null},{"id":"2502.15980","title":"Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2510.09671","title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2402.08666","title":"Improving Generalization in Semantic Parsing by Increasing Natural Language Variation","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.14305","title":"JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2505.23838","title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2301.04110","title":"Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2405.01588","title":"Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2406.00014","title":"KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2406.16349","title":"AnnotatedTables: A Large Tabular Dataset with Language Model Annotations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2502.11022","title":"MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translation","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2507.14372","title":"Text-to-SQL for Enterprise Data Analytics","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2601.09876","title":"Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2601.14698","title":"ClaimDB: A Fact Verification Benchmark over Large Structured Data","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2602.22223","title":"SQaLe: A Large Text-to-SQL Corpus Grounded in Real Schemas","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2510.01989","title":"Exploring Database Normalization Effects on SQL Generation","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2603.07841","title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2506.23273","title":"FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysis","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2510.27532","title":"SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2601.13111","title":"CORE-T: COherent REtrieval of Tables for Text-to-SQL","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.03363","title":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2609.08950","title":"SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2210.07201","title":"Searching for Better Database Queries in the Outputs of Semantic Parsers","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2506.23071","title":"Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2510.02394","title":"Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsing","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2603.23375","title":"Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.24023","title":"Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.25568","title":"Are LLMs Overkill for Databases?: A Study on the Finiteness of SQL","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2606.08245","title":"ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.06229","title":"Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.23569","title":"ESQ-Bench: A Multi-Tier Enterprise Oracle Benchmark for Evaluating NL2SQL Dialect Generalization and Silent Semantic Divergence","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.26172","title":"DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.29345","title":"BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.22259","title":"Which Part of the Context Layer Does the Work? Separating Semantic Content from Retrieval Scaffolding in Text-to-SQL Agents","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}