Evaluating GPT-4's Cognitive Functions Through the Bloom Taxonomy: Insights and Clarifications

被引：1
|
作者：
Herrmann-Werner, Anne [1 ,2 ]
Festl-Wietek, Teresa [1 ]
Holderried, Friederike [1 ,3 ]
Herschbach, Lea [1 ]
Griewatz, Jan [1 ]
Masters, Ken [4 ]
Zipfel, Stephan [2 ]
Mahling, Moritz [1 ,5 ]
机构：
[1] Univ Tubingen, Tubingen Inst Med Educ, Fac Med, Elfriede Aulhorn Str 10, D-72076 Tubingen, Germany
[2] Univ Hosp Tubingen, Dept Psychosomat Med & Psychotherapy, Tubingen, Germany
[3] Univ Tubingen, Tubingen Univ Hosp, Dept Anesthesiol & Intens Care Med, Tubingen, Germany
[4] Sultan Qaboos Univ, Coll Med & Hlth Sci, Med Educ & Informat Dept, Muscat, Oman
[5] Univ Hosp Tubingen, Dept Diabetol Endocrinol Nephrol, Sect Nephrol & Hypertens, Tubingen, Germany
来源：
JOURNAL OF MEDICAL INTERNET RESEARCH | 2024年 / 26卷
关键词：
answer; artificial intelligence; assessment; Bloom's taxonomy; ChatGPT; classification; error; exam; examination; generative; GPT-4; Generative Pre-trained Transformer 4; language model; learning outcome; LLM; MCQ; medical education; medical exam; multiple-choice question; natural language processing; NLP; psychosomatic; question; response; taxonomy;
D O I：
10.2196/57778
中图分类号：
R19 [保健组织与事业（卫生事业管理）];
学科分类号：
摘要：
引用
收藏
页数：2
相关论文
共 50 条
  • [21] Evaluating Four Corners Textbooks in Terms of Cognitive Processes Using Bloom's Revised Taxonomy
    Roohani, Ali
    Taheri, Farzaneh
    Poorzangeneh, Marziyeh
    JOURNAL OF RESEARCH IN APPLIED LINGUISTICS, 2013, 4 (02): : 51 - 67
  • [22] Evaluating prompt engineering on GPT-3.5's performance in USMLE-style medical calculations and clinical scenarios generated by GPT-4
    Patel, Dhavalkumar
    Raut, Ganesh
    Zimlichman, Eyal
    Cheetirala, Satya Narayan
    Nadkarni, Girish N.
    Glicksberg, Benjamin S.
    Apakama, Donald U.
    Bell, Elijah J.
    Freeman, Robert
    Timsina, Prem
    Klang, Eyal
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [23] Generative AI Meets Animal Welfare: Evaluating GPT-4 for Pet Emotion Detection
    Cetintav, Bekir
    Guven, Yavuz Selim
    Gulek, Engincan
    Akbas, Aykut Asim
    ANIMALS, 2025, 15 (04):
  • [24] Evaluating capabilities of large language models: Performance of GPT-4 on surgical knowledge assessments
    Beaulieu-Jones, Brendin R.
    Berrigan, Margaret T.
    Shah, Sahaj
    Marwaha, Jayson S.
    Lai, Shuo-Lun
    Brat, Gabriel A.
    SURGERY, 2024, 175 (04) : 936 - 942
  • [25] GPT-4-Trinis: assessing GPT-4's communicative competence in the English-speaking majority world
    Jackson, Samantha
    Beekhuizen, Barend
    Zhao, Zhao
    Mcewen, Rhonda
    AI & SOCIETY, 2024, 40 (3) : 1785 - 1801
  • [26] Evaluating Large Language Models for the National Premedical Exam in India: Comparative Analysis of GPT-3.5, GPT-4, and Bard
    Farhat, Faiza
    Chaudhry, Beenish Moalla
    Nadeem, Mohammad
    Sohail, Shahab Saquib
    Madsen, Dag Oivind
    JMIR MEDICAL EDUCATION, 2024, 10
  • [27] Evaluating student performance based on bloom’s taxonomy levels
    Prasad, G.N.R.
    Journal of Physics: Conference Series, 2021, 1797 (01)
  • [28] More Than Meets the AI: Evaluating the performance of GPT-4 on Computer Graphics assessment questions
    Feng, Tony Haoran
    Denny, Paul
    Wuensche, Burkhard C.
    Luxton-Reilly, Andrew
    Hooper, Steffan
    PROCEEDINGS OF THE 26TH AUSTRALASIAN COMPUTING EDUCATION CONFERENCE, ACE 2024, 2024, : 182 - 191
  • [29] GPT-4's Performance on the European Board of Interventional Radiology Sample Questions
    Besler, Muhammed Said
    CARDIOVASCULAR AND INTERVENTIONAL RADIOLOGY, 2024, 47 (05) : 683 - 684
  • [30] GPT-4's Performance on the European Board of Interventional Radiology Sample Questions
    Muhammed Said Beşler
    CardioVascular and Interventional Radiology, 2024, 47 : 683 - 684
12345