{"list":"other","total":57,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"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":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"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":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2004.00584","title":"Deep Entity Matching with Pre-Trained Language Models","created":"2020-04-01","cited_by_count":144},{"id":"2408.09174","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","created":"2024-08-17","cited_by_count":128},{"id":"1703.07469","title":"RobustFill: Neural Program Learning under Noisy I/O","created":"2017-03-21","cited_by_count":126},{"id":"2305.13062","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","created":"2023-05-22","cited_by_count":116},{"id":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106},{"id":"1905.10688","title":"Sherlock: A Deep Learning Approach to Semantic Data Type Detection","created":"2019-05-25","cited_by_count":74},{"id":"2310.09263","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","created":"2023-10-13","cited_by_count":69},{"id":"2305.19308","title":"SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models","created":"2023-05-30","cited_by_count":57},{"id":"1805.11234","title":"Table-to-Text: Describing Table Region with Natural Language","created":"2018-05-29","cited_by_count":41},{"id":"2106.15339","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","created":"2021-06-26","cited_by_count":41},{"id":"2104.01785","title":"Annotating Columns with Pre-trained Language Models","created":"2021-04-05","cited_by_count":37},{"id":"2010.07386","title":"Valentine: Evaluating Matching Techniques for Dataset Discovery","created":"2020-10-14","cited_by_count":35},{"id":"2406.19073","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","created":"2024-06-27","cited_by_count":35},{"id":"2109.05877","title":"Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation","created":"2021-09-13","cited_by_count":30},{"id":"2310.07875","title":"TabLib: A Dataset of 627M Tables with Context","created":"2023-10-11","cited_by_count":23},{"id":"2005.11490","title":"Summarizing and Exploring Tabular Data in Conversational Search","created":"2020-05-23","cited_by_count":19},{"id":"2307.14565","title":"Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples","created":"2023-07-27","cited_by_count":15},{"id":"2101.01507","title":"A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumeration","created":"2021-01-05","cited_by_count":14},{"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},{"id":"2310.07736","title":"Observatory: Characterizing Embeddings of Relational Tables","created":"2023-10-05","cited_by_count":12},{"id":"2404.12608","title":"Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations","created":"2024-04-19","cited_by_count":12},{"id":"2411.05000","title":"Needle Threading: Can LLMs Follow Threads through Near-Million-Scale Haystacks?","created":"2024-11-07","cited_by_count":12},{"id":"1708.08721","title":"EntiTables: Smart Assistance for Entity-Focused Tables","created":"2017-08-29","cited_by_count":11},{"id":"2109.11020","title":"Exploring Decomposition for Table-based Fact Verification","created":"2021-09-22","cited_by_count":11},{"id":"2309.01957","title":"Automatic Data Transformation Using Large Language Model: An Experimental Study on Building Energy Data","created":"2023-09-05","cited_by_count":8},{"id":"2306.12515","title":"Auto-BI: Automatically Build BI-Models Leveraging Local Join Prediction and Global Schema Graph","created":"2023-06-21","cited_by_count":7},{"id":"2504.11627","title":"Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence","created":"2025-04-15","cited_by_count":5},{"id":"2301.13095","title":"Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V (Technical Report)","created":"2023-01-30","cited_by_count":3},{"id":"2303.06748","title":"DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models","created":"2023-03-12","cited_by_count":3},{"id":"1705.09276","title":"Synthesizing Mapping Relationships Using Table Corpus","created":"2017-05-25","cited_by_count":2},{"id":"2504.10762","title":"Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables","created":"2025-04-14","cited_by_count":2},{"id":"2312.06296","title":"Measuring Approximate Functional Dependencies: a Comparative Study","created":"2023-12-11","cited_by_count":1}],"next_cursor":null}