The study explores the capabilities of OpenAI's ChatGPT in solving different types of physics problems. ChatGPT (with GPT-4) was queried to solve a total of 40 problems from a college-level engineering physics course. These problems ranged from well-specified problems, where all data required for solving the problem was provided, to under-specified, real-world problems where not all necessary data were given. Our findings show that ChatGPT could successfully solve 62.5% of the well-specified problems, but its accuracy drops to 8.3% for under-specified problems. Analysis of the model's incorrect solutions revealed three distinct failure modes: 1) failure to construct accurate models of the physical world, 2) failure to make reasonable assumptions about missing data, and 3) calculation errors. The study offers implications for how to leverage LLM-augmented instructional materials to enhance STEM education. The insights also contribute to the broader discourse on AI's strengths and limitations, serving both educators aiming to leverage the technology and researchers investigating human-AI collaboration frameworks for problem-solving and decision-making.
From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT
MGEN -- College of Engineering, Northeastern University Miami(东北大学迈阿密分校MGEN工程学院);University of Vermont(佛蒙特大学);AGH, University of Krakow(克拉科夫AGH大学);Howard University(霍华德大学)
Deutsche Welle(德国之声);Universitat Politecnica de Valencia(瓦伦西亚理工大学);ABC News(美国广播公司新闻部);Bonn-Aachen International Center for Information Technology (b-it), University of Bonn(波恩大学波恩-亚琛国际信息技术中心);The Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所)
ChatGPT and Works Scholarly: Best Practices and Legal Pitfalls in Writing with AI
University of California, Irvine(加利福尼亚大学欧文分校);Te Herenga Waka - Victoria University of Wellington(惠灵顿维多利亚大学(Te Herenga Waka));University of Kansas(堪萨斯大学);MIT Sloan School of Management(麻省理工学院斯隆管理学院)
Mapping the Challenges of HCI: An Application and Evaluation of ChatGPT for Mining Insights at Scale
University of Oulu, Center for Applied Computing, Faculty of Information Technology and Electrical Engineering(奥卢大学,应用计算中心,信息科技与电气工程学院);University of Jyväskylä, Software and Communications Engineering, Faculty of Information Technology(耶夫尼耶斯基大学,软件与通信工程,信息科技学院)
Exploring the Impact of Generative Artificial Intelligence in Education: A Thematic Analysis
Dundalk Institute of Technology(唐道克理工学院);Dublin Business School(都柏林商学院);University College Dublin(都柏林大学学院);Technological University Dublin(都柏林理工大学);Jagan Institute of Management Studies(贾根管理学院)
Examining the Commitments and Difficulties Inherent in Multimodal Foundation Models for Street View Imagery
Guanghua School of Management, Peking University(北京大学光华管理学院);The Bartlett School of Sustainable Construction, University College London(伦敦大学学院巴特lett可持续建筑学院);School of Architecture, Tsinghua University(清华大学建筑学院);School of Computing, The University of Georgia(佐治亚大学计算学院);Department of Geography, University College London(伦敦大学学院地理系);Department of Geography and the Environment, University of Texas at Austin(德克萨斯大学奥斯汀分校地理与环境系)
Institute of Computational Life Sciences, Zurich University of Applied Sciences(计算生命科学学院,应用科学大学);Institute of History and Philosophy of Science and Technology (IHPST), Université Paris 1 - Panthéon-Sorbonne(科学与技术历史与哲学研究所,巴黎第一大学)
Faculty of Automation and Computer Science, Technical University of Cluj-Napoca(自动化与计算机科学学院,克莱斯-纳波卡技术大学);Artificial Intelligence Research Institute, Technical University of Cluj-Napoca(人工智能研究所,克莱斯-纳波卡技术大学);Faculty of Civil Engineering, Technical University of Cluj-Napoca(土木工程学院,克莱斯-纳波卡技术大学);School of Art and Design, Technological University Dublin(艺术与设计学院,都柏林技术大学);European Culture and Technology Laboratory, European University of Technology(欧洲文化与技术实验室,欧洲技术大学)