{"list":"other","total":80,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"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":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2105.04165","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","created":"2021-05-10","cited_by_count":383},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192},{"id":"2305.12474","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","created":"2023-05-21","cited_by_count":186},{"id":"2304.02015","title":"How well do Large Language Models perform in Arithmetic tasks?","created":"2023-03-16","cited_by_count":130},{"id":"2010.06354","title":"The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT","created":"2020-10-13","cited_by_count":128},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110},{"id":"1812.08693","title":"An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation","created":"2018-12-20","cited_by_count":108},{"id":"2106.03830","title":"A Simple Recipe for Multilingual Grammatical Error Correction","created":"2021-06-07","cited_by_count":108},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89},{"id":"2212.09292","title":"ChatGPT: The End of Online Exam Integrity?","created":"2022-12-19","cited_by_count":88},{"id":"2203.13947","title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","created":"2022-03-26","cited_by_count":80},{"id":"2009.11506","title":"Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems","created":"2020-09-24","cited_by_count":60},{"id":"2309.14049","title":"How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment","created":"2023-09-25","cited_by_count":56},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51},{"id":"2307.15020","title":"SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark","created":"2023-07-27","cited_by_count":50},{"id":"2303.11146","title":"On the Educational Impact of ChatGPT: Is Artificial Intelligence Ready to Obtain a University Degree?","created":"2023-03-20","cited_by_count":48},{"id":"2309.08221","title":"Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study","created":"2023-09-15","cited_by_count":44},{"id":"2302.06871","title":"Learning gain differences between ChatGPT and human tutor generated algebra hints","created":"2023-02-14","cited_by_count":43},{"id":"2403.09539","title":"Logits of API-Protected LLMs Leak Proprietary Information","created":"2024-03-14","cited_by_count":40},{"id":"2306.10073","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","created":"2023-06-15","cited_by_count":39},{"id":"2312.03173","title":"A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education","created":"2023-12-05","cited_by_count":35},{"id":"2403.03008","title":"Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations","created":"2024-03-05","cited_by_count":31},{"id":"1609.07197","title":"Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems","created":"2016-09-23","cited_by_count":28},{"id":"2209.14876","title":"Repairing Bugs in Python Assignments Using Large Language Models","created":"2022-09-29","cited_by_count":28},{"id":"2402.14601","title":"Bringing Generative AI to Adaptive Learning in Education","created":"2024-02-02","cited_by_count":24},{"id":"2307.13923","title":"GrammarGPT: Exploring Open-Source LLMs for Native Chinese Grammatical Error Correction with Supervised Fine-Tuning","created":"2023-07-26","cited_by_count":23},{"id":"2311.02775","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","created":"2023-11-05","cited_by_count":22},{"id":"2311.17394","title":"Deepfakes, Misinformation, and Disinformation in the Era of Frontier AI, Generative AI, and Large AI Models","created":"2023-11-29","cited_by_count":21},{"id":"2103.16997","title":"UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language","created":"2021-03-31","cited_by_count":19},{"id":"2306.09064","title":"Learning by Analogy: Diverse Questions Generation in Math Word Problem","created":"2023-06-15","cited_by_count":18},{"id":"2402.18502","title":"Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification","created":"2024-02-28","cited_by_count":18},{"id":"2201.05590","title":"Czech Grammar Error Correction with a Large and Diverse Corpus","created":"2022-01-14","cited_by_count":17},{"id":"2402.07956","title":"Educational data mining and learning analytics: An updated survey","created":"2024-02-10","cited_by_count":17},{"id":"2312.02065","title":"Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?","created":"2023-12-04","cited_by_count":16},{"id":"2101.10074","title":"Personalized Education in the AI Era: What to Expect Next?","created":"2021-01-19","cited_by_count":13},{"id":"2306.01815","title":"Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scale","created":"2023-06-02","cited_by_count":12},{"id":"2307.16696","title":"Large Language Models for Education: Grading Open-Ended Questions Using ChatGPT","created":"2023-07-31","cited_by_count":11},{"id":"2402.12150","title":"Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One","created":"2024-02-19","cited_by_count":11},{"id":"2403.05636","title":"Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach","created":"2024-03-08","cited_by_count":11},{"id":"1912.00839","title":"Automatic Generation of Headlines for Online Math Questions","created":"2019-11-27","cited_by_count":10},{"id":"1512.09176","title":"Personalized Course Sequence Recommendations","created":"2015-12-30","cited_by_count":9},{"id":"2312.11890","title":"Difficulty-Focused Contrastive Learning for Knowledge Tracing with a Large Language Model-Based Difficulty Prediction","created":"2023-12-19","cited_by_count":9},{"id":"2312.14969","title":"Challenges and Opportunities of Moderating Usage of Large Language Models in Education","created":"2023-12-19","cited_by_count":9},{"id":"1909.10166","title":"Automatic Short Answer Grading via Multiway Attention Networks","created":"2019-09-23","cited_by_count":8},{"id":"2305.13114","title":"Exploring User Perspectives on ChatGPT: Applications, Perceptions, and Implications for AI-Integrated Education","created":"2023-05-22","cited_by_count":8},{"id":"2401.01692","title":"Predicting challenge moments from students' discourse: A comparison of GPT-4 to two traditional natural language processing approaches","created":"2024-01-03","cited_by_count":8},{"id":"2210.13964","title":"Learning to Reuse Distractors to support Multiple Choice Question Generation in Education","created":"2022-10-25","cited_by_count":7},{"id":"2208.05681","title":"Overview of CTC 2021: Chinese Text Correction for Native Speakers","created":"2022-08-11","cited_by_count":6},{"id":"2311.04906","title":"FlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation","created":"2023-09-26","cited_by_count":5},{"id":"2308.01776","title":"Does Correction Remain A Problem For Large Language Models?","created":"2023-08-03","cited_by_count":3},{"id":"2309.13500","title":"Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy","created":"2023-09-23","cited_by_count":3},{"id":"2311.06207","title":"Vox Populi, Vox ChatGPT: Large Language Models, Education and Democracy","created":"2023-11-10","cited_by_count":3},{"id":"2305.14507","title":"Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models","created":"2023-05-23","cited_by_count":2},{"id":"2306.00190","title":"Contextualizing Problems to Student Interests at Scale in Intelligent Tutoring System Using Large Language Models","created":"2023-05-31","cited_by_count":2},{"id":"2401.04601","title":"Imagining Computing Education Assessment after Generative AI","created":"2024-01-09","cited_by_count":2}],"next_cursor":null}