The Personification of ChatGPT (GPT-4)-Understanding Its Personality and Adaptability

被引:2
|
作者
Stockli, Leandro [1 ]
Joho, Luca [1 ]
Lehner, Felix [1 ]
Hanne, Thomas [2 ]
机构
[1] Univ Appl Sci & Arts Northwestern Switzerland, Sch Business, CH-4600 Olten, Switzerland
[2] Univ Appl Sci & Arts Northwestern Switzerland, Inst Informat Syst, CH-4600 Olten, Switzerland
关键词
transformer-based language models; ChatGPT; personality; personality tests; INDICATOR MBTI;
D O I
10.3390/info15060300
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Thanks to the publication of ChatGPT, Artificial Intelligence is now basically accessible and usable to all internet users. The technology behind it can be used in many chatbots, whereby the chatbots should be trained for the respective area of application. Depending on the application, the chatbot should react differently and thus, for example, also take on and embody personality traits to be able to help and answer people better and more personally. This raises the question of whether ChatGPT-4 is able to embody personality traits. Our study investigated whether ChatGPT-4's personality can be analyzed using personality tests for humans. To test possible approaches to measuring the personality traits of ChatGPT-4, experiments were conducted with two of the most well-known personality tests: the Big Five and Myers-Briggs. The experiments also examine whether and how personality can be changed by user input and what influence this has on the results of the personality tests.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Performance of ChatGPT and GPT-4 on Polish National Specialty Exam (NSE) in Ophthalmology
    Ciekalski, Marcin
    Laskowski, Maciej
    Koperczak, Agnieszka
    Smierciak, Maria
    Sirek, Sebastian
    POSTEPY HIGIENY I MEDYCYNY DOSWIADCZALNEJ, 2024, 78 (01): : 111 - 116
  • [22] ChatGPT surges ahead: GPT-4 has arrived in the arena of medical research
    Wang, Ying-Mei
    Chen, Tzeng-Ji
    JOURNAL OF THE CHINESE MEDICAL ASSOCIATION, 2023, 86 (09) : 784 - 785
  • [23] Improving the Readability of Generated Tests Using GPT-4 and ChatGPT Code Interpreter
    Gay, Gregory
    SEARCH-BASED SOFTWARE ENGINEERING, SSBSE 2023, 2024, 14415 : 140 - 146
  • [24] Artificial Intelligence in Intensive Care Medicine: Toward a ChatGPT/GPT-4 Way?
    Yanqiu Lu
    Haiyang Wu
    Shaoyan Qi
    Kunming Cheng
    Annals of Biomedical Engineering, 2023, 51 : 1898 - 1903
  • [25] Is GPT-4 a reliable rater? Evaluating consistency in GPT-4's text ratings
    Hackl, Veronika
    Mueller, Alexandra Elena
    Granitzer, Michael
    Sailer, Maximilian
    FRONTIERS IN EDUCATION, 2023, 8
  • [26] Large language models such as ChatGPT and GPT-4 for patient-centered care in radiology
    Fink, Matthias A.
    RADIOLOGIE, 2023, 63 (09): : 665 - 671
  • [27] ChatGPT, GPT-4, and Other Large Language Models: The Next Revolution for Clinical Microbiology?
    Egli, Adrian
    CLINICAL INFECTIOUS DISEASES, 2023, 77 (09) : 1322 - 1328
  • [28] ChatGPT With GPT-4 Outperforms Emergency Department Physicians in Diagnostic Accuracy: Retrospective Analysis
    Hoppe, John Michael
    Auer, Matthias K.
    Strueven, Anna
    Massberg, Steffen
    Stremmel, Christopher
    JOURNAL OF MEDICAL INTERNET RESEARCH, 2024, 26
  • [29] Beyond ChatGPT: What does GPT-4 add to healthcare? The dawn of a new era
    Wojcik, Simona
    Rulkiewicz, Anna
    Pruszczyk, Piotr
    Lisik, Wojciech
    Pobozy, Marcin
    Domienik-Karlowicz, Justyna
    CARDIOLOGY JOURNAL, 2023, 30 (06) : 1018 - 1025
  • [30] GPT-4 Vision: Multi-Modal Evolution of ChatGPT and Potential Role in Radiology
    Javan, Ramin
    Kim, Theodore
    Mostaghni, Navid
    CUREUS JOURNAL OF MEDICAL SCIENCE, 2024, 16 (08)