一句话：用动态微调与持续学习策略让LLM适应代码库演化，实现缺陷模块预测。
软件快速演化使缺陷预测模型必须频繁重训练才能保持有效，而LLM虽已广泛用于软件工程任务，其在演化数据集上的质量保障应用（尤其是缺陷预测）仍缺乏探索。本文研究动态微调技术，使LLM能够在代码库持续演化的情况下预测缺陷模块。作者首先整理了QuixBugs及多个GitHub项目构成的数据集，随后采用动态微调方法让LLM适配演化数据集，并使用弹性权重巩固（EWC）与记忆回放等持续学习策略评估模型以缓解灾难性遗忘。初步结果表明，LLaMA-LoRA、PolyCoder、StarCoder等LLM经动态微调后，在演化数据集上可取得与CodeBERT、GraphCodeBERT、CodeT5等中等规模模型相当的性能。本文据此提供了LLM用于软件质量保障的早期证据与反思，并勾勒出大规模模型缺陷预测的未来研究方向。
Software evolves rapidly, making it challenging for defect prediction models to remain effective without frequent retraining. While the Large Language Models (LLMs) have been widely used in SE tasks, their application to evolving datasets for quality assurance, particularly defect prediction, remains under-explored. This study investigates the use of dynamic fine-tuning techniques to enable LLMs to predict defective modules in the face of codebase evolution. We begin our study by curating datasets such as the publicly available QuixBugs and multiple GitHub software projects. We followed a dynamic-fine-tuning approach to adopt the LLMs for the evolving datasets. To mitigate catastrophic forgetting, the LLMs are then evaluated using continual learning strategies such as Elastic Weight Consolidation and memory replay. Preliminary results indicate that LLMs such as LLaMA-LoRA, PolyCoder, and StarCoder when dynamically fine-tuned, achieved comparative performance on medium-sized models such as CodeBERT, GraphCodeBERT, and CodeT5 across evolving datasets. Through this preliminary study, we provide early evidence and reflections on the promise of LLMs for software quality assurance and outline research directions that can shape the future of defect prediction using large-scale models.
@inproceedings{paperbot9178,
title = {LLMs for Defect Prediction in Evolving Datasets: Emerging Results and Future Directions},
author = {Umamaheswara Sharma Bhutamapuram and Farhan Chonari and Gokul K Anilkumar and Sai Kiran Konchada},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728491}
}