相关论文: On the Reliability of Code Comprehension Proxies

The field of information retrieval often works with limited and noisy data in an attempt to classify documents into subjective categories, e.g., relevance, sentiment and controversy. We typically quantify a notion of agreement to understand…

Compilers are widely-used infrastructures in accelerating the software development, and expected to be trustworthy. In the literature, various testing technologies have been proposed to guarantee the quality of compilers. However, there…

Code pre-trained models (CodePTMs) have recently demonstrated significant success in code intelligence. To interpret these models, some probing methods have been applied. However, these methods fail to consider the inherent characteristics…

Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To address this challenge, researchers have begun applying various…

Important building blocks of software engineering concepts are without a doubt technical. During the last decade, research and practical interest for non-technicalities has grown, revealing the building blocks to be various skills and…

We explore an approach to verification of programs via program transformation applied to an interpreter of a programming language. A specialization technique known as Turchin's supercompilation is used to specialize some interpreters with…

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

Recent papers show LLMs achieve near-random accuracy in causal relation classification, raising questions about whether such failures arise from limited pretraining exposure or deeper representational gaps. We investigate this under…

Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by…

Empirical software engineering research on production systems has brought forth a better understanding of the software engineering process for practitioners and researchers alike. However, only a small subset of production systems is…

Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool…

We explore an approach to verification of programs via program transformation applied to an interpreter of a programming language. A specialization technique known as Turchin's supercompilation is used to specialize some interpreters with…

In-context learning (ICL) is a pivotal capability for the practical deployment of large-scale language models, yet its reliability can vary substantially with the number of demonstrations provided in the prompt. A central obstacle is that…

The goal of selective prediction is to allow an a model to abstain when it may not be able to deliver a reliable prediction, which is important in safety-critical contexts. Existing approaches to selective prediction typically require…

Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmarks primarily evaluate final output correctness under a…

Code generation models are widely used in software development, yet their sensitivity to prompt phrasing remains under-examined. Identical requirements expressed with different emotions or communication styles can yield divergent outputs,…

When solving optimization problems under uncertainty with contextual data, utilizing machine learning to predict the uncertain parameters' values is a popular and effective approach. Decision-focused learning (DFL) aims at learning a…

Software needs to be secure, in particular, when deployed to critical infrastructures. Secure coding guidelines capture practices in industrial software engineering to ensure the security of code. This study aims to assess the level of…

With the rapid growth of Android malware, many machine learning-based malware analysis approaches are proposed to mitigate the severe phenomenon. However, such classifiers are opaque, non-intuitive, and difficult for analysts to understand…

Context: Software Engineering research makes use of collections of software artifacts (corpora) to derive empirical evidence from. Goal: To improve quality and reproducibility of research, we need to understand the characteristics of used…