{"total":53,"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":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187,"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":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2305.14215","title":"Exploring Chain-of-Thought Style Prompting for Text-to-SQL","created":"2023-05-23","cited_by_count":69,"area":"lr"},{"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":"2305.11853","title":"How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings","created":"2023-05-19","cited_by_count":58,"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":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52,"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":"2306.14321","title":"RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations","created":"2023-06-25","cited_by_count":43,"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":"2310.17894","title":"Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","created":"2023-10-27","cited_by_count":27,"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":"2310.06302","title":"Selective Demonstrations for Cross-domain Text-to-SQL","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2310.07736","title":"Observatory: Characterizing Embeddings of Relational Tables","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2505.17231","title":"ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects","created":"2025-05-22","cited_by_count":12,"area":"synth"},{"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":"2412.12522","title":"Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL","created":"2024-12-17","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":"2412.12612","title":"Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2508.00217","title":"Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges","created":"2025-07-31","cited_by_count":10,"area":"mllm"},{"id":"2603.10697","title":"EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution","created":"2026-03-11","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":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2508.16265","title":"M3TQA: Massively Multilingual Multitask Table Question Answering","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2503.01457","title":"Structural Deep Encoding for Table Question Answering","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2509.04657","title":"Evaluating NL2SQL via SQL2NL","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2407.15071","title":"Relational Database Augmented Large Language Model","created":"2024-07-21","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":"2511.04120","title":"RIDE: Difficulty Evolving Perturbation with Item Response Theory for Mathematical Reasoning","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2511.13590","title":"Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2601.02739","title":"Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.04086","title":"KDCM: Reducing Hallucination in LLMs through Explicit Reasoning Structures","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2604.06736","title":"SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.16493","title":"NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.00628","title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","created":"2026-05-01","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":"2511.04710","title":"GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2512.18622","title":"A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback","created":"2025-12-21","cited_by_count":0,"area":"agents"},{"id":"2601.10318","title":"Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis","created":"2026-01-15","cited_by_count":0,"area":"synth"},{"id":"2605.03465","title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.02109","title":"BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2607.03833","title":"Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.24145","title":"TrustDABench: Benchmarking Reliability and Robustness of LLMs for Structured Data Analysis","created":"2026-08-25","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":"2609.00834","title":"Replacing Training with Memory: Listwise Selection for Text-to-SQL","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.34783","title":"TQTS-Bench: A Multi-Syntax Benchmark for Text-to-Query over Time-Series Databases","created":"2026-09-28","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},{"id":"2610.06914","title":"A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.14700","title":"DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}