Intent-Aware Defect Pattern Extraction from Singular Examples
Open Access
- 25 June 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Abstract
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.Keywords
This publication has 36 references indexed in Scilit:
- GRACE: Empowering LLM-based software vulnerability detection with graph structure and in-context learningJournal of Systems and Software, 2024
- Explaining Software Bugs Leveraging Code Structures in Neural Machine Translation2023
- HEDF: A Method for Early Forecasting Software Defects Based on Human Error MechanismsIEEE Access, 2023
- FixMiner: Mining relevant fix patterns for automated program repairEmpirical Software Engineering, 2020
- Inferring Program Transformations From Singular Examples via Big Code2019
- Why don't software developers use static analysis tools to find bugs?2013
- Model Transformation By-Example: A Survey of the First Wave2012
- Toward an understanding of bug fix patternsEmpirical Software Engineering, 2008
- Model Transformation by Example2006
- A critique of software defect prediction modelsIEEE Transactions on Software Engineering, 1999