{"total":33,"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":"2306.15681","title":"ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram","created":"2023-06-21","cited_by_count":54,"area":null},{"id":"2310.18652","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","created":"2023-10-28","cited_by_count":53,"area":null},{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"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":"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":"2511.10192","title":"Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL","created":"2025-11-13","cited_by_count":11,"area":null},{"id":"2412.05208","title":"A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges","created":"2024-12-06","cited_by_count":10,"area":null},{"id":"2405.07896","title":"Almanac Copilot: Towards Autonomous Electronic Health Record Navigation","created":"2024-04-30","cited_by_count":9,"area":null},{"id":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2310.08759","title":"Question Answering for Electronic Health Records: A Scoping Review of datasets and models","created":"2023-10-12","cited_by_count":7,"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":"2405.01588","title":"Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2507.01053","title":"M3: Conversational LLMs Simplify Secure Clinical Data Access, Understanding, and Analysis","created":"2025-06-27","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":"2411.00266","title":"A Systematic Review of NeurIPS Dataset Management Practices","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2512.13297","title":"MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data","created":"2025-12-15","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":"2512.16189","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2601.10020","title":"EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2603.16434","title":"From Natural Language to Executable Option Strategies via Large Language Models","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2510.00549","title":"EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.00772","title":"Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2511.17559","title":"SCARE: A Benchmark for SQL Correction and Question Answerability Classification for Reliable EHR Question Answering","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2512.22744","title":"Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2602.18452","title":"RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.23479","title":"FHIRPath-QA: Executable Question Answering over FHIR Electronic Health Records","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.21414","title":"SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.05525","title":"Anatomy of a Query: W5H Dimensions and FAR Patterns for Text-to-SQL Evaluation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.29503","title":"The Verbose Context Problem in Medical Records","created":"2026-06-28","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":"2609.30027","title":"Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.02576","title":"Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}