Zbornik radova Fakulteta tehničkih nauka

Inženjerstvo informacionih sistema

God. 41 Br. 07 (2026): Зборник радова Факултета техничких наука

Употреба великих језичких модела у тестирању софтвера

  • David Feješ
DOI:
https://doi.org/10.24867/35OI03Fejes
Predato
November 2, 2026
Objavljeno
2026-07-15

Apstrakt

Развој генеративне вештачке интелигенције омогућио је широку примену великих језичких модела у различитим доменима развоја софтвера. Велики језички модели се све чешће користе као подршка у фазама аутоматизације, анализе и евалуације тестова, повећавајући ефикасност тестирања. Овај рад се бави улогом и потенцијалом великих језичких модела у савременом тестирању софтвера, са посебним освртом на његове предности, ограничења и факторе који утичу на поузданост. Посебна пажња посвећена је питању поузданости и стабилности модела, што представља кључни изазов у практичној примени. Резултати указују да велики језички модели тренутно имају највећу вредност као подршка постојећим алатима и методама, док њихова пуна аутономија захтева даља истраживања.

Reference

  1. [1] R. F. de L. Junior, L. F. P. de B. Presta, L. S. Borborema, V. N. da Silva, M. L. de M. Dahia, and A. C. S. e Santos, “A Case Study on Test Case Construction with Large Language Models: Unveiling Practical Insights and Challenges,” Dec. 2023, [Online]. Available: http://arxiv.org/abs/2312.12598
  2. [2] M. Schäfer, S. Nadi, A. Eghbali, and F. Tip, “An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation,” Dec. 2023, [Online]. Available: http://arxiv.org/abs/2302.06527
  3. [3] Y. Chen, Z. Hu, C. Zhi, J. Han, S. Deng, and J. Yin, “ChatUniTest: A Framework for LLM-Based Test Generation,” in FSE Companion - Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, Association for Computing Machinery, Inc, Jul. 2024, pp. 572–576. doi: 10.1145/3663529.3663801.
  4. [4] S. Karpurapu et al., “Comprehensive Evaluation and Insights Into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation,” IEEE Access, vol. 12, pp. 58715–58721, 2024, doi: 10.1109/ACCESS.2024.3391815.
  5. [5] G. Yi, Z. Chen, Z. Chen, W. E. Wong, and N. Chau, “Exploring the Capability of ChatGPT in Test Generation,” in Proceedings - 2023 IEEE 23rd International Conference on Software Quality, Reliability, and Security Companion, QRS-C 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 72–80. doi: 10.1109/QRS-C60940.2023.00013.
  6. [6] A. Lops, F. Narducci, A. Ragone, and M. Trizio, “AgoneTest: Automated creation and assessment of Unit tests leveraging Large Language Models,” in Proceedings - 2024 39th ACM/IEEE International Conference on Automated Software Engineering, ASE 2024, Association for Computing Machinery, Inc, Oct. 2024, pp. 2440–2441. doi: 10.1145/3691620.3695318.
  7. [7] H. Koziolek, V. Ashiwal, S. Bandyopadhyay, and C. K. R, “Automated Control Logic Test Case Generation using Large Language Models,” May 2024, [Online]. Available: http://arxiv.org/abs/2405.01874
  8. [8] A. Guo et al., “SoVAR: Build Generalizable Scenarios from Accident Reports for Autonomous Driving Testing,” in Proceedings - 2024 39th ACM/IEEE International Conference on Automated Software Engineering, ASE 2024, Association for Computing Machinery, Inc, Oct. 2024, pp. 268–280. doi: 10.1145/3691620.3695037.
  9. [9] Z. Wang, K. Liu, G. Li, and Z. Jin, “HITS: High-coverage LLM-based Unit Test Generation via Method Slicing,” Aug. 2024, [Online]. Available: http://arxiv.org/abs/2408.11324
  10. [10] T. Le, T. Tran, D. Cao, V. Le, T. Nguyen, and V. Nguyen, “KAT: Dependency-aware Automated API Testing with Large Language Models,” Jul. 2024, doi: 10.1109/ICST60714.2024.00017.
  11. [11] L. Yang et al., “On the Evaluation of Large Language Models in Unit Test Generation,” in Proceedings - 2024 39th ACM/IEEE International Conference on Automated Software Engineering, ASE 2024, Association for Computing Machinery, Inc, Oct. 2024, pp. 1607–1619. doi: 10.1145/3691620.3695529.
  12. [12] T.-O. Li et al., “Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting,” Sep. 2023, [Online]. Available: http://arxiv.org/abs/2304.11686
  13. [13] S. Kang, J. Yoon, N. Askarbekkyzy, and S. Yoo, “Evaluating Diverse Large Language Models for Automatic and General Bug Reproduction,” Nov. 2023, [Online]. Available: http://arxiv.org/abs/2311.04532
  14. [14] S. Bhatia, T. Gandhi, D. Kumar, and P. Jalote, “Unit Test Generation using Generative AI : A Comparative Performance Analysis of Autogeneration Tools,” Feb. 2024, [Online]. Available: http://arxiv.org/abs/2312.10622
  15. [15] A. M. Dakhel, A. Nikanjam, V. Majdinasab, F. Khomh, and M. C. Desmarais, “Effective Test Generation Using Pre-trained Large Language Models and Mutation Testing,” Aug. 2023, [Online]. Available: http://arxiv.org/abs/2308.16557
  16. [16] C. Lemieux, J. Priya Inala, S. K. Lahiri, and S. Sen, “CODAMOSA: Escaping Coverage Plateaus in Test Generation with Pre-trained Large Language Models.” [Online]. Available: https://github.com/microsoft/codamosa.
  17. [17] K. El Haji, C. Brandt, and A. Zaidman, “Using GitHub Copilot for Test Generation in Python: An Empirical Study,” in Proceedings - 2024 IEEE/ACM International Conference on Automation of Software Test, AST 2024, Association for Computing Machinery, Inc, Apr. 2024, pp. 45–55. doi: 10.1145/3644032.3644443.
  18. [18] S. Kang, J. Yoon, and S. Yoo, “Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction,” Jul. 2023, [Online]. Available: http://arxiv.org/abs/2209.11515
  19. [19] M. Nabeel, D. D. Nimara, and T. Zanouda, “Test Code Generation for Telecom Software Systems using Two-Stage Generative Model,” Apr. 2024, [Online]. Available: http://arxiv.org/abs/2404.09249
  20. [20] J. Hoffmann and D. Frister, “Generating Software Tests for Mobile Applications Using Fine-Tuned Large Language Models,” in Proceedings - 2024 IEEE/ACM International Conference on Automation of Software Test, AST 2024, Association for Computing Machinery, Inc, Apr. 2024, pp. 76–77. doi: 10.1145/3644032.3644454.
  21. [21] N. Alshahwan et al., “Automated Unit Test Improvement using Large Language Models at Meta,” in FSE Companion - Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, Association for Computing Machinery, Inc, Jul. 2024, pp. 185–196. doi: 10.1145/3663529.3663839.
  22. [22] A. Deljouyi, “Understandable Test Generation Through Capture/Replay and LLMs,” in Proceedings - International Conference on Software Engineering, IEEE Computer Society, Apr. 2024, pp. 261–263. doi: 10.1145/3639478.3639789.
  23. [23] L. Plein, W. C. Ouédraogo, J. Klein, and T. F. Bissyandé, “Automatic Generation of Test Cases based on Bug Reports: A Feasibility Study with Large Language Models,” in Proceedings - International Conference on Software Engineering, IEEE Computer Society, Apr. 2024, pp. 360–361. doi: 10.1145/3639478.3643119.