{"total":22,"rows":[{"id":"2501.09310","title":"Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors","created":"2025-01-16","cited_by_count":14,"area":null},{"id":"2412.10138","title":"ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL","created":"2024-12-13","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":"2409.19014","title":"FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark","created":"2024-09-24","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":"2508.15276","title":"AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL","created":"2025-08-21","cited_by_count":11,"area":null},{"id":"2510.23854","title":"Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2502.00329","title":"CoddLLM: Empowering Large Language Models for Data Analytics","created":"2025-02-01","cited_by_count":6,"area":null},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2502.11438","title":"SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL","created":"2025-02-17","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":"2510.26840","title":"SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2508.14056","title":"Confidence Estimation for Text-to-SQL in Large Language Models","created":"2025-08-08","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":"2604.25149","title":"Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2510.02350","title":"LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.23284","title":"DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Model","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2609.25938","title":"Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQL","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.30290","title":"Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.00092","title":"BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.02122","title":"Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03625","title":"FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}