.png){kind=icon}
返回
Measuring model alignment for code clone detection using causal interpretation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10664-024-10583-0.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep Neural Network-based models have demonstrated high accuracy for semantic code clone detection. However, the lack of generalization poses a threat to the trustworthiness and reliability of these models. Furthermore, the black-box nature of these models makes interpreting the model's decisions very challenging. Currently, there is only a limited understanding of the semantic code clone detection behavior of existing models. There is a lack of transparency in understanding how a model identifies semantic code clones and the exact code components influencing its prediction. In this paper, we introduce the use of a causal interpretation framework based on the Neyman-Rubin causal model to gain insight into the decision-making of four state-of-the-art clone detection models. Using the causal interpretation framework, we derive causal explanations of models' decisions by performing interventions guided by expert-labeled data. We measure the alignment of models' decision-making with expert intuition by evaluating the causal effects of code similarities and differences on the clone predictions of the models. Additionally, we evaluate the similarity intuition alignment, robustness to confounding influences, and prediction consistency of the models. Finally, we rank the models in order of most aligned and thus most reliable to least aligned and thus least reliable for semantic code clone detection. Our contributions lay a foundation for building and evaluating trustworthy semantic code clone detection systems.
Keyword:
Explainable AI
Model interpretation
Semantic code clones
Causal inference
Model alignment
Interpreting clone detection
期刊
IF:
3.6
论文数:
2.0K
被引数:
5.3K
机构
引用论文
Long noncoding RNA hypoxia-inducible factor 1 alpha-antisense RNA 1 promotes tumor necrosis factor-α-induced apoptosis through caspase 3 in Kupffer cells.png)
Medicine
OAAI
MedicineIF0
OAAI分享收藏分享收藏Lys63/Met1-hybrid ubiquitin chains are commonly formed during the activation of innate immune signallingLys63/Met1-hybrid泛素链通常在先天免疫信号激活过程中形成OAAI
OAAI分享收藏Volcanic, Coseismic, and Seasonal Changes Detected at White Island (Whakaari) Volcano, New Zealand, Using Seismic Ambient Noise使用地震环境噪声在新西兰怀特岛 (Whakaari) 火山检测到的火山，同震和季节变化OAAI
OAAI分享收藏
查看更多内容