A Systematic Literature Review on Explainability for ML/DL-based Software Engineering
ACM Computing Surveys · 31.03.2026 · 58 (4) · 1-34
DOI: 10.1145/3763230 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift ACM Computing Surveys, online erschienen am 25.10.2025. Verfasst von Sicong Cao und 10 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 177 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Jiangsu “333” Project; the Open Project of Industry-Education Integration Innovation Center of Specialized Cybersecurity.
Abstract (Originalsprache)
The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE). However, due to their black-box nature, these promising AI-driven SE models are still far from being deployed in practice. This lack of explainability poses unwanted risks for their applications in critical tasks, such as vulnerability detection, where decision-making transparency is of paramount importance. This article endeavors to elucidate this interdisciplinary domain by presenting a systematic literature review of approaches that aim to improve the explainability of AI models within the context of SE. The review canvasses work appearing in the most prominent SE and AI conferences and journals, and spans 108 articles across 23 unique SE tasks. Based on three key Research Questions (RQs), we aim to (1) summarize the SE tasks where XAI techniques have shown success to date; (2) classify and analyze different XAI techniques; and (3) investigate existing evaluation approaches. Based on our findings, we identified a set of challenges remaining to be addressed in existing studies, together with a set of guidelines highlighting potential opportunities we deemed appropriate and important for future work.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Jiangsu “333” Project; the Open Project of Industry-Education Integration Innovation Center of Specialized Cybersecurity
- Open Foundation of Yunnan Key Laboratory of Software Engineering
- National Research Foundation, under its Investigatorship Grant
Zitieren
APA
Cao, S., Sun, X., Widyasari, R., Lo, D., Wu, X., Bo, L., Zhang, J., Li, B., Liu, W., Wu, D., & Chen, Y. (2026). A Systematic Literature Review on Explainability for ML/DL-based Software Engineering. ACM Computing Surveys, 58(4), 1-34. https://doi.org/10.1145/3763230
Vancouver
Cao S, Sun X, Widyasari R, Lo D, Wu X, Bo L, et al. A Systematic Literature Review on Explainability for ML/DL-based Software Engineering. ACM Computing Surveys. 2026;58(4):1-34. doi:10.1145/3763230
BibTeX
@article{Cao2026,
author = {Cao, Sicong and Sun, Xiaobing and Widyasari, Ratnadira and Lo, David and Wu, Xiaoxue and Bo, Lili and Zhang, Jiale and Li, Bin and Liu, Wei and Wu, Di and Chen, Yixin},
title = {A Systematic Literature Review on Explainability for ML/DL-based Software Engineering},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {4},
pages = {1--34},
doi = {10.1145/3763230}
}
EUVIMED