.png){kind=icon}
返回
Explainable automated debugging via large language model-driven scientific debugging
.png){kind=icon}
OA
AI
DOI：10.1007/s10664-024-10594-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automated debugging techniques have the potential to reduce developer effort in debugging. However, while developers want rationales for the provided automatic debugging results, existing techniques are ill-suited to provide them, as their deduction process differs significantly froof human developers. Inspired by the way developers interact with code when debugging, we propose Automated Scientific Debugging (AutoSD), a technique that prompts large language models to automatically generate hypotheses, uses debuggers to interact with buggy code, and thus automatically reach conclusions prior to patch generation. In doing so, we aim to produce explanations of how a specific patch has been generated, with the hope that these explanations will lead to enhanced developer decision-making. Our empirical analysis on three program repair benchmarks shows that AutoSDperforms competitively with other program repair baselines, and that it can indicate when it is confident in its results. Furthermore, we perform a human study with 20 participants to evaluate AutoSD-generated explanations. Participants with access to explanations judged patch correctness more accurately in five out of six real-world bugs studied. Furthermore, 70% of participants answered that they wanted explanations when using repair tools, and 55% answered that they were satisfied with the Scientific Debugging presentation.
Keyword:
Automated Program Repair
Machine Learning
期刊
IF:
3.6
论文数:
2.0K
被引数:
5.3K
机构
引用论文
Polysialylated Neural Cell Adhesion Molecule Is Involved in Induction of Long-Term Potentiation and Memory Acquisition and Consolidation in a Fear-Conditioning Paradigm聚唾液酸化的神经细胞粘附分子在恐惧调节范式中参与诱导长期增强和记忆获取和巩固
OAAI
.png){kind=icon}
OAAI分享收藏Microscale forced combustion: Pyrolysis-combustion flow calorimetry (PCFC)微尺度强制燃烧: 热解-燃烧流量量热法 (PCFC)
PREAI
分享收藏分享收藏Astor: Exploring the design space of generate-and-validate program repair beyond GenProgAstor: 探索GenProg之外的生成和验证程序修复的设计空间OAAI
OAAI分享收藏
查看更多内容