{"list":"other","total":78,"rows":[{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"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},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2304.11015","title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","created":"2023-04-21","cited_by_count":477},{"id":"2004.02349","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","created":"2020-04-05","cited_by_count":434},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235},{"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},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"2401.04398","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","created":"2024-01-09","cited_by_count":188},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167},{"id":"2010.10439","title":"Open Question Answering over Tables and Text","created":"2020-10-20","cited_by_count":163},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"2311.09206","title":"TableLlama: Towards Open Large Generalist Models for Tables","created":"2023-11-15","cited_by_count":137},{"id":"2010.12773","title":"Structure-Grounded Pretraining for Text-to-SQL","created":"2020-10-24","cited_by_count":126},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121},{"id":"2108.06712","title":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","created":"2021-08-15","cited_by_count":118},{"id":"2105.02584","title":"TABBIE: Pretrained Representations of Tabular Data","created":"2021-05-06","cited_by_count":111},{"id":"2106.01065","title":"Towards Robustness of Text-to-SQL Models against Synonym Substitution","created":"2021-06-02","cited_by_count":110},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106},{"id":"2405.01147","title":"Why Tabular Foundation Models Should Be a Research Priority","created":"2024-05-02","cited_by_count":106},{"id":"2010.12537","title":"TUTA: Tree-based Transformers for Generally Structured Table Pre-training","created":"2020-10-21","cited_by_count":100},{"id":"2109.05157","title":"Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization","created":"2021-09-11","cited_by_count":92},{"id":"2004.10404","title":"Logical Natural Language Generation from Open-Domain Tables","created":"2020-04-22","cited_by_count":90},{"id":"1901.07931","title":"Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge","created":"2019-01-23","cited_by_count":86},{"id":"2005.06117","title":"INFOTABS: Inference on Tables as Semi-structured Data","created":"2020-05-13","cited_by_count":86},{"id":"1904.03396","title":"Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation","created":"2019-04-06","cited_by_count":75},{"id":"2411.14199","title":"OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs","created":"2024-11-21","cited_by_count":72},{"id":"2408.07702","title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","created":"2024-08-14","cited_by_count":67},{"id":"2310.17342","title":"ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought","created":"2023-10-26","cited_by_count":65},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53},{"id":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52},{"id":"2305.13186","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","created":"2023-05-22","cited_by_count":51},{"id":"2004.14356","title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","created":"2020-04-29","cited_by_count":48},{"id":"2109.02707","title":"Text-to-Table: A New Way of Information Extraction","created":"2021-09-06","cited_by_count":47},{"id":"2004.14579","title":"Logic2Text: High-Fidelity Natural Language Generation from Logical Forms","created":"2020-04-30","cited_by_count":45},{"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},{"id":"2106.05006","title":"Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data","created":"2021-06-09","cited_by_count":43},{"id":"2305.07288","title":"Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table","created":"2023-05-12","cited_by_count":40},{"id":"2312.13671","title":"Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries","created":"2023-12-21","cited_by_count":38},{"id":"2010.01891","title":"A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese","created":"2020-10-05","cited_by_count":36},{"id":"2105.13995","title":"SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)","created":"2021-05-28","cited_by_count":35},{"id":"1909.13293","title":"A Pilot Study for Chinese SQL Semantic Parsing","created":"2019-09-29","cited_by_count":33},{"id":"2404.14215","title":"Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction","created":"2024-04-22","cited_by_count":33},{"id":"2305.12820","title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","created":"2023-05-22","cited_by_count":32},{"id":"2310.18538","title":"Evaluating Cross-Domain Text-to-SQL Models and Benchmarks","created":"2023-10-27","cited_by_count":32},{"id":"2312.09039","title":"TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning","created":"2023-12-14","cited_by_count":32},{"id":"2212.09994","title":"Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation","created":"2022-12-20","cited_by_count":28},{"id":"2311.08002","title":"TempTabQA: Temporal Question Answering for Semi-Structured Tables","created":"2023-11-14","cited_by_count":27},{"id":"2404.09889","title":"Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval","created":"2024-04-15","cited_by_count":27},{"id":"2305.14336","title":"Schema-Driven Information Extraction from Heterogeneous Tables","created":"2023-05-23","cited_by_count":25},{"id":"2105.01736","title":"Retrieving Complex Tables with Multi-Granular Graph Representation Learning","created":"2021-05-04","cited_by_count":24},{"id":"2302.03815","title":"Long Text and Multi-Table Summarization: Dataset and Method","created":"2023-02-08","cited_by_count":23},{"id":"2212.13492","title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","created":"2022-12-27","cited_by_count":22},{"id":"2010.09394","title":"Knowledge Graph-based Question Answering with Electronic Health Records","created":"2020-10-19","cited_by_count":19},{"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},{"id":"2403.15879","title":"TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring","created":"2024-03-23","cited_by_count":17},{"id":"2404.18585","title":"FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering","created":"2024-04-29","cited_by_count":16},{"id":"2104.08296","title":"Learning to Reason for Text Generation from Scientific Tables","created":"2021-04-16","cited_by_count":14},{"id":"2310.13196","title":"NameGuess: Column Name Expansion for Tabular Data","created":"2023-10-19","cited_by_count":13},{"id":"2501.03540","title":"Deep Learning within Tabular Data: Foundations, Challenges, Advances and Future Directions","created":"2025-01-07","cited_by_count":9},{"id":"2406.14829","title":"Is This a Bad Table? A Closer Look at the Evaluation of Table Generation from Text","created":"2024-06-21","cited_by_count":8},{"id":"2402.08496","title":"A Systematic Review of Data-to-Text NLG","created":"2024-02-13","cited_by_count":4},{"id":"2412.14146","title":"ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics","created":"2024-12-18","cited_by_count":4},{"id":"2307.03313","title":"InfoSync: Information Synchronization across Multilingual Semi-structured Tables","created":"2023-07-06","cited_by_count":3},{"id":"2404.04103","title":"Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo","created":"2024-04-05","cited_by_count":3},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3},{"id":"2501.00057","title":"VisTabNet: Adapting Vision Transformers for Tabular Data","created":"2024-12-28","cited_by_count":2}],"next_cursor":null}