A survey on deep learning for software engineering

Y Yang, X **a, D Lo, J Grundy - ACM Computing Surveys (CSUR), 2022 - dl.acm.org
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 …

When software security meets large language models: A survey

X Zhu, W Zhou, QL Han, W Ma, S Wen… - IEEE/CAA Journal of …, 2025 - ieeexplore.ieee.org
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 …

Automating code review activities by large-scale pre-training

Z Li, S Lu, D Guo, N Duan, S Jannu, G Jenks… - Proceedings of the 30th …, 2022 - dl.acm.org
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 …

Retrieval-augmented generation for code summarization via hybrid gnn

S Liu, Y Chen, X **e, J Siow, Y Liu - arxiv preprint arxiv:2006.05405, 2020 - arxiv.org
Source code summarization aims to generate natural language summaries from structured
code snippets for better understanding code functionalities. However, automatic code …

Exploring the capabilities of llms for code change related tasks

L Fan, J Liu, Z Liu, D Lo, X **a, S Li - ACM Transactions on Software …, 2024 - dl.acm.org
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 …

LLaMA-Reviewer: Advancing code review automation with large language models through parameter-efficient fine-tuning

J Lu, L Yu, X Li, L Yang, C Zuo - 2023 IEEE 34th International …, 2023 - ieeexplore.ieee.org
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 …

Learning program semantics with code representations: An empirical study

JK Siow, S Liu, X **e, G Meng… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Program semantics learning is the core and fundamental for various code intelligent tasks
eg, vulnerability detection, clone detection. A considerable amount of existing works …

Atom: Commit message generation based on abstract syntax tree and hybrid ranking

S Liu, C Gao, S Chen, LY Nie… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
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 …

[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 …

Spi: Automated identification of security patches via commits

Y Zhou, JK Siow, C Wang, S Liu, Y Liu - ACM Transactions on Software …, 2021 - dl.acm.org
Security patches in open source software, providing security fixes to identified
vulnerabilities, are crucial in protecting against cyber attacks. Security advisories and …