Zobrazeno 1 - 10
of 195
pro vyhledávání: '"D.2.3"'
This paper presents our findings on the automatic summarization of Java methods within Ericsson, a global telecommunications company. We evaluate the performance of an approach called Automatic Semantic Augmentation of Prompts (ASAP), which uses a La
Externí odkaz:
http://arxiv.org/abs/2408.09735
Autor:
Sun, Weisong, Chen, Yuchen, Fang, Chunrong, Feng, Yebo, Xiao, Yuan, Guo, An, Zhang, Quanjun, Liu, Yang, Xu, Baowen, Chen, Zhenyu
Neural code models (NCMs) have been widely used for addressing various code understanding tasks, such as defect detection and clone detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCM
Externí odkaz:
http://arxiv.org/abs/2408.04683
We present the Code Documentation and Analysis Tool (CoDAT). CoDAT is a tool designed to maintain consistency between the various levels of code documentation, e.g. if a line in a code sketch is changed, the comment that documents the corresponding c
Externí odkaz:
http://arxiv.org/abs/2407.11934
Machine learning models trained on code and related artifacts offer valuable support for software maintenance but suffer from interpretability issues due to their complex internal variables. These concerns are particularly significant in safety-criti
Externí odkaz:
http://arxiv.org/abs/2407.08890
Autor:
Sun, Weisong, Miao, Yun, Li, Yuekang, Zhang, Hongyu, Fang, Chunrong, Liu, Yi, Deng, Gelei, Liu, Yang, Chen, Zhenyu
To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, t
Externí odkaz:
http://arxiv.org/abs/2407.07959
Autor:
Fang, Chunrong, Sun, Weisong, Chen, Yuchen, Chen, Xiao, Wei, Zhao, Zhang, Quanjun, You, Yudu, Luo, Bin, Liu, Yang, Chen, Zhenyu
(Source) code summarization aims to automatically generate succinct natural language summaries for given code snippets. Such summaries play a significant role in promoting developers to understand and maintain code. Inspired by neural machine transla
Externí odkaz:
http://arxiv.org/abs/2407.01646
Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets are problematic: either using unrealistic queries, or with mismatch
Externí odkaz:
http://arxiv.org/abs/2406.11589
Recent advancements in Large Language Models (LLMs) and their utilization in code generation tasks have significantly reshaped the field of software development. Despite the remarkable efficacy of code completion solutions in mainstream programming l
Externí odkaz:
http://arxiv.org/abs/2405.15729
Refactoring is one of the most important activities in software engineering which is used to improve the quality of a software system. With the advancement of deep learning techniques, researchers are attempting to apply deep learning techniques to s
Externí odkaz:
http://arxiv.org/abs/2404.19226
Autor:
Kamiya, Toshihiro
Although the context length limitation of large language models (LLMs) has been mitigated, it still hinders their application to software development tasks. This study proposes a method incorporating execution traces into RAG for inquiries about sour
Externí odkaz:
http://arxiv.org/abs/2404.06082