{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"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":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"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":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"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":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"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":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267},{"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":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2504.11354","title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","created":"2025-04-15","cited_by_count":180},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175},{"id":"2312.11242","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","created":"2023-12-18","cited_by_count":164},{"id":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140},{"id":"2408.09174","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","created":"2024-08-17","cited_by_count":128},{"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":"2405.12209","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","created":"2024-05-20","cited_by_count":105},{"id":"2305.06090","title":"XTab: Cross-table Pretraining for Tabular Transformers","created":"2023-05-10","cited_by_count":81},{"id":"2411.02059","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","created":"2024-11-04","cited_by_count":72},{"id":"2404.19205","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","created":"2024-04-30","cited_by_count":69},{"id":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52},{"id":"2106.12944","title":"AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry","created":"2021-06-24","cited_by_count":44},{"id":"2406.07436","title":"McEval: Massively Multilingual Code Evaluation","created":"2024-06-11","cited_by_count":44},{"id":"2311.15296","title":"UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation","created":"2023-11-26","cited_by_count":22},{"id":"2505.14415","title":"Table Foundation Models: on knowledge pre-training for tabular learning","created":"2025-05-20","cited_by_count":19},{"id":"2411.19504","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","created":"2024-11-29","cited_by_count":17},{"id":"2311.09829","title":"FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models","created":"2023-11-16","cited_by_count":12},{"id":"2310.15075","title":"TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering","created":"2023-10-23","cited_by_count":7}],"next_cursor":null}