Intent-Aware Defect Pattern Extraction from Singular Examples
ACM Transactions on Software Engineering and Methodology · 25.06.2026
DOI: 10.1145/3820049 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 25.06.2026. Verfasst von Jiachen Han und 7 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben.
Abstract (Originalsprache)
As software systems grow in complexity, particularly in safety-critical domains, detecting defects early is crucial to prevent severe failures. Among existing automated defect detection methods, rule-based systems excel at catching well-understood mistakes but are hard to generalize beyond their predefined rules. To address this challenge, we introduce DslGen, a novel approach that automatically extracts high-quality defect patterns from singular defect repair examples by leveraging large language models (LLMs). Specifically, it first infers the semantic intent of a defect repair for capturing the defect’s essential characteristics via LLM-powered analysis, then generates precise constraint rules to define the defect pattern. Unlike prior methods, DslGen does not require numerous examples or rigid abstraction schemes, enabling robust generalization even from a single fix. To evaluate the effectiveness of DslGen, we evaluated it in two distinct scenarios: (1) controlled experiments and (2) a simulated real-world defect detection pipeline. In the controlled setting, results show that DslGen outperforms all baselines, achieving a precision up to 81.1% and a recall of over 73.0%. In the simulated scenario, DslGen also performed best with an average improvement of 425.1% over state-of-the-art competitors (including GPT-4o). A user study with 15 experienced developers further confirmed DslGen’s practicality, with participants praising the readability and generalizability of its generated DSLs and expressing strong adoption intent.
Zitieren
APA
Han, J., Li, F., Jiang, J., Fan, R., Xiong, Y., Pan, L., Wang, B., & Chen, J. (2026). Intent-Aware Defect Pattern Extraction from Singular Examples. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3820049
Vancouver
Han J, Li F, Jiang J, Fan R, Xiong Y, Pan L, et al. Intent-Aware Defect Pattern Extraction from Singular Examples. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3820049
BibTeX
@article{Han2026,
author = {Han, Jiachen and Li, Fengjie and Jiang, Jiajun and Fan, Ruihang and Xiong, Yingfei and Pan, Linjie and Wang, Bilian and Chen, Junjie},
title = {Intent-Aware Defect Pattern Extraction from Singular Examples},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
doi = {10.1145/3820049}
}
EUVIMED