SUN’IY INTELLEKT (LLM) YORDAMIDA EKVIVALENT MUTANTLARNI FILTRLASH VA SHAXSIYLASHTIRILGAN TESKARI ALOQA GENERATSIYALASH

• Xurshidbek Komiljon o‘g‘li Xamrayev

  Author

Mazkur maqolada mutatsion testlashning ikki asosiy to‘sig‘i — ekvivalent mutantlarni aniqlashning yechib bo‘lmas muammosi va yuqori hisoblash xarajatlarini katta til modellari (LLM) yordamida hal etish imkoniyati ko‘rib chiqilgan. LLM-modulning ikki vazifasi — ekvivalent mutantlarni filtrlash va talaba profiliga moslab tushuntiruvchi teskari aloqa generatsiyalash loyihalangan. Tahlil shuni ko‘rsatdiki, LLM lar dastur semantikasini chuqurroq qamrab ekvivalent mutant aniqlashda istiqbolli natija beradi, biroq “gallyutsinatsiya” va noto‘g‘ri takliflar xavfi saqlanib qoladi. Shu bois inson nazorati (human-in-the-loop) zarurligi asoslangan.

1. Jia, Y., & Harman, M. (2011). An Analysis and Survey of the Development of Mutation Testing. IEEE Transactions on Software Engineering, 37(5), 649–678.

2. Roest, L., Keuning, H., & Jeuring, J. (2024). Evaluating the Application of Large Language Models to Generate Feedback in Programming Education. arXiv:2403.09744.

3. Tian, Z., Shu, J., Zhan, Y., et al. (2024). Large Language Models for Equivalent Mutant Detection: How Far Are We? Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA). https://doi.org/10.1145/3650212.3680395

4. Open Source Language Models Can Provide Feedback: Evaluating LLMs’ Ability to Help Students Using GPT-4-As-A-Judge. (2024). Proceedings of ITiCSE 2024. https://doi.org/10.1145/3649217.3653612

5. Messer, M., Brown, N. C. C., Kölling, M., & Shi, M. (2024). Automated Grading and Feedback Tools for Programming Education: A Systematic Review. ACM Transactions on Computing Education, 24(1), 1–43. https://doi.org/10.1145/3636515

• PDF|Download