EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automating Severity Prediction of Bug Reports Using Large Language Models (LLM)

Nasir Rashid, Mustafa Bilal, Muneeb Babar, Sheraz Babar, Pervez Khan, Muhammad Salam

International Journal of Innovations in Science and Technology · 28.06.2026 · 1485

DOI: 10.33411/ijist/1941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 28.06.2026. Verfasst von Nasir Rashid und 5 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of bug report severity is essential for prioritizing software-maintenance activities, but manual severity assignment is costly, time-consuming, and potentially inconsistent. This study investigates prompt-based open-weight Large Language Models for automatically classifying bug reports as severe or non-severe without task-specific fine-tuning. The experiments used 3,535 bug reports from the CDT, JDT, Bugzilla, and Thunderbird projects. The original severity labels were mapped into two categories: blocker, critical, and major as severe, and normal, minor, and trivial as non-severe. LLaMA 3.1:8B and Qwen3:8B were evaluated under zero-shot and few-shot prompting and compared with Support Vector Machine, Multinomial Naive Bayes, Random Forest, and Long Short-Term Memory models using TF-IDF and Word2Vec representations. On the held-out test set, Qwen3:8B with few-shot prompting achieved 98.6% accuracy, 100% precision, 97.5% recall, and a 98.7% F1-score. Compared with the strongest conventional baseline, Random Forest with TF-IDF, it improved accuracy and F1-score by 26.6 and 24.2 percentage points, respectively. On an additional dataset of 200 synthetically generated bug reports, LLaMA 3.1:8B with zero-shot prompting achieved 97.99% accuracy and a 98.51% F1-score, while Qwen3:8B with few-shot prompting achieved 97.9% accuracy and a 97.5% F1-score. These results indicate that prompt-based LLMs can substantially reduce task-specific preprocessing and training requirements while providing high predictive performance. However, further evaluation on independent, human-authored, cross-project datasets is required before making broad claims regarding real-world generalization.

Zitieren

APA

Rashid, N., Bilal, M., Babar, M., Babar, S., Khan, P., & Salam, M. (2026). Automating Severity Prediction of Bug Reports Using Large Language Models (LLM). International Journal of Innovations in Science and Technology, 1485. https://doi.org/10.33411/ijist/1941

Vancouver

Rashid N, Bilal M, Babar M, Babar S, Khan P, Salam M. Automating Severity Prediction of Bug Reports Using Large Language Models (LLM). International Journal of Innovations in Science and Technology. 2026:1485. doi:10.33411/ijist/1941

BibTeX
@article{Rashid2026,
  author = {Rashid, Nasir and Bilal, Mustafa and Babar, Muneeb and Babar, Sheraz and Khan, Pervez and Salam, Muhammad},
  title = {Automating Severity Prediction of Bug Reports Using Large Language Models (LLM)},
  journal = {International Journal of Innovations in Science and Technology},
  year = {2026},
  pages = {1485},
  doi = {10.33411/ijist/1941}
}
Kostenlos starten →