Related papers: Context-Specific Instruction: A Longitudinal Study…
Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) provided to models for fine-tuning, they achieved much higher…
The joint task of bug localization and program repair is an integral part of the software development process. In this work we present DeepDebug, an approach to automated debugging using large, pretrained transformers. We begin by training…
In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in methods that rely on weight updates. Recently, a few studies…
Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. This study investigates structuring training data to enhance…
Many studies have long investigated how developers debug, shaping our understanding of debugging and helping motivate the creation of more effective tools. However, less is known about the typical progression of debugging in real world…
Bug triaging, the task of assigning new issues to developers, is often slow and inconsistent in large projects. We present a lightweight framework that instruction-tuned large language model (LLM) with LoRA adapters and uses…
Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles.…
Real bug fixes found in open source repositories seem to be the perfect source for learning to localize and repair real bugs. However, the absence of large scale bug fix collections has made it difficult to effectively exploit real bug…
Generative deep learning (DL) models have been successfully adopted for vulnerability patching. However, such models require the availability of a large dataset of patches to learn from. To overcome this issue, researchers have proposed to…
Motivation: Automated bug detection in dynamically typed languages such as Python is essential for maintaining code quality. The lack of mandatory type annotations in such languages can lead to errors that are challenging to identify early…
Providing effective feedback for programming assignments in computer science education can be challenging: students solve problems by iteratively submitting code, executing it, and using limited feedback from the compiler or the auto-grader…
Context-bounded analysis has been shown to be both efficient and effective at finding bugs in concurrent programs. According to its original definition, context-bounded analysis explores all behaviors of a concurrent program up to some…
Symbolic quick error detection (SQED) has greatly improved efficiency in formal chip verification. However, it has a limitation in detecting single-instruction bugs due to its reliance on the self-consistency property. To address this, we…
Making errors is part of the programming process -- even for the most seasoned professionals. Novices in particular are bound to make many errors while learning. It is well known that traditional (compiler/interpreter) programming error…
The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we…
Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…
Software bugs cost technology providers (e.g., AT&T) billions annually and cause developers to spend roughly 50% of their time on bug resolution. Traditional methods for bug localization often analyze the suspiciousness of code components…
Bug localization in object oriented program ha s always been an important issue in softeware engineering. In this paper, I propose a source level bug localization technique for object oriented embedded programs. My proposed technique,…
The SZZ algorithm is the dominant technique for identifying bug-inducing commits and serves as a foundation for many software engineering studies, such as bug prediction and static code analysis. Researchers have proposed many variants to…
Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…