Abstract

This study evaluated ChatGPT's capacity to pass the Turing test in the Kyrgyz language by comparing the responses of humans and artificial intelligence. As findings revealed, 56% of the participants could distinguish ChatGPT's responses from human responses, while the remaining 44% perceived them as human-like. These findings suggest that while ChatGPT can occasionally generate responses that bear a resemblance to human-like answers, it does not fully meet the criteria for passing the Turing test.Statistical analyses revealed that ChatGPT demonstrated higher performance in factual and cognitive questions but exhibited a divergence from human intuition in answering psychological and personal preference-related questions.The study's results underscore the necessity for further adaptation of artificial intelligence to the Kyrgyz language

Keywords

Kyrgyz language , Turing Test , ChatGPT, NLP, Artificial Intelligence

References

  1. Anatolievich, K.M. (2020). Criticism of J. Searle's Chinese room argument. Moscow University Bulletin. Series 7. Philosophy, 3, article number 3.

  2. Development of artificial intelligence. (n.d.). Retrieved from https://cyberleninka.ru/article/n/razvitie-iskusstvennogo-intellekta/viewer.

  3. Selwyn, N. (2022). The future of AI and education: Some cautionary notes. European Journal of Education, 57(4), 620-631. doi: 10.1111/ejed.12532.

  4. Keleş, H. (2022). Artificial intelligence applications in medicine. Kırıkkale University Faculty of Medicine Journal, 24(3), 604-613. doi: 10.24938/kutfd.1214512.

  5. He, J., Baxter, S.L., Xu, J., Xu, J., Zhou, X., & Zhang, K. (2019). The practical implementation of artificial intelligence technologies in medicine. Nature Medicine, 25(1), 30-36. doi: 10.1038/s41591-018-0307-0.

  6. İşler, B., & Kılıç, M. (2021). The use and development of artificial intelligence in education. New Media Electronic Journal, 5(1).

  7. Jalolov, T.S. (2024). Creating diagnostic systems based on artificial intelligence in healthcare. Methods and Applications of Innovative Digital Technologies in Education Systems, 1(2).

  8. Black, D. (1969). Lewis Carroll and the theory of games. American Economic Review, 59(2), 206-210.

  9. Mihalcea, R., Liu, H., & Lieberman, H. (2006). NLP (Natural Language Processing) for NLP (Natural Language Programming). In A. Gelbukh (Ed.), Computational linguistics and intelligent text processing (pp. 319-330). Heidelberg: Springer. doi: 10.1007/11671299_34.

  10. Altintas, V., & Kilinc, M. (2024). Automated categorization of Turkish e-commerce product reviews using BERTurk. In 2024 8th international artificial intelligence and data processing symposium (IDAP) (pp. 1-6). New York: IEEE. doi: 10.1109/IDAP64064.2024.10710859.

  11. Dam, S.K., Hong, C.S., Qiao, Y., & Zhang, C. (2024). A complete survey on LLM-based AI chatbots. arXiv. doi: 10.48550/arXiv.2406.16937.

  12. Saygin, A.P., Cicekli, I., & Akman, V. (2000). Turing test: 50 years later. Minds and Machines, 10(4), 463-518. doi: 10.1023/A:1011288000451.

  13. Hodges, A. (2009). Alan Turing and the Turing test. In R. Epstein, G. Roberts & G. Beber (Eds.), Parsing the Turing test (pp. 13-22). Heidelberg: Springer. doi: 10.1007/978-1-4020-6710-5_2.

  14. Paschen, J. (2019). Investigating the emotional appeal of fake news using artificial intelligence and human contributions. Journal of Product & Brand Management, 29(2), 223-233. doi: 10.1108/JPBM-12-2018-2179.

Suggested citation

Erkinova, N., Sharshebaev, B., & Ismailova, R. (2025). EVALUATING CHATGPT'S ABILITY TO PASS THE TURING TEST IN KYRGYZ LANGUAGE. News of Osh Technological University, 25(1), 51-61.