A survey on deep learning for software engineering
In 2006, Geoffrey Hinton proposed the concept of training “Deep Neural Networks (DNNs)”
and an improved model training method to break the bottleneck of neural network …
and an improved model training method to break the bottleneck of neural network …
When software security meets large language models: A survey
Software security poses substantial risks to our society because software has become part of
our life. Numerous techniques have been proposed to resolve or mitigate the impact of …
our life. Numerous techniques have been proposed to resolve or mitigate the impact of …
Automating code review activities by large-scale pre-training
Code review is an essential part to software development lifecycle since it aims at
guaranteeing the quality of codes. Modern code review activities necessitate developers …
guaranteeing the quality of codes. Modern code review activities necessitate developers …
Retrieval-augmented generation for code summarization via hybrid gnn
Source code summarization aims to generate natural language summaries from structured
code snippets for better understanding code functionalities. However, automatic code …
code snippets for better understanding code functionalities. However, automatic code …
Exploring the capabilities of llms for code change related tasks
Developers deal with code-change-related tasks daily, eg, reviewing code. Pre-trained code
and code-change-oriented models have been adapted to help developers with such tasks …
and code-change-oriented models have been adapted to help developers with such tasks …
LLaMA-Reviewer: Advancing code review automation with large language models through parameter-efficient fine-tuning
The automation of code review activities, a long-standing pursuit in software engineering,
has been primarily addressed by numerous domain-specific pre-trained models. Despite …
has been primarily addressed by numerous domain-specific pre-trained models. Despite …
Learning program semantics with code representations: An empirical study
Program semantics learning is the core and fundamental for various code intelligent tasks
eg, vulnerability detection, clone detection. A considerable amount of existing works …
eg, vulnerability detection, clone detection. A considerable amount of existing works …
Atom: Commit message generation based on abstract syntax tree and hybrid ranking
Commit messages record code changes (eg, feature modifications and bug repairs) in
natural language, and are useful for program comprehension. Due to the frequent updates …
natural language, and are useful for program comprehension. Due to the frequent updates …
[PDF][PDF] Unifying the perspectives of nlp and software engineering: A survey on language models for code
Z Zhang, C Chen, B Liu, C Liao, Z Gong… - arxiv preprint arxiv …, 2023 - simg.baai.ac.cn
In this work we systematically review the recent advancements in code processing with
language models, covering 50+ models, 30+ evaluation tasks, 170+ datasets, and 700 …
language models, covering 50+ models, 30+ evaluation tasks, 170+ datasets, and 700 …
Spi: Automated identification of security patches via commits
Security patches in open source software, providing security fixes to identified
vulnerabilities, are crucial in protecting against cyber attacks. Security advisories and …
vulnerabilities, are crucial in protecting against cyber attacks. Security advisories and …