Large language models for software engineering: A systematic literature review

X Hou, Y Zhao, Y Liu, Z Yang, K Wang, L Li… - ACM Transactions on …, 2024 - dl.acm.org
Large Language Models (LLMs) have significantly impacted numerous domains, including
Software Engineering (SE). Many recent publications have explored LLMs applied to …

Software testing with large language models: Survey, landscape, and vision

J Wang, Y Huang, C Chen, Z Liu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Pre-trained large language models (LLMs) have recently emerged as a breakthrough
technology in natural language processing and artificial intelligence, with the ability to …

Structured chain-of-thought prompting for code generation

J Li♂, G Li, Y Li, Z Jin - ACM Transactions on Software Engineering and …, 2023 - dl.acm.org
Large Language Models (LLMs) have shown impressive abilities in code generation. Chain-
of-Thought (CoT) prompting is the state-of-the-art approach to utilizing LLMs. CoT prompting …

Refining chatgpt-generated code: Characterizing and mitigating code quality issues

Y Liu, T Le-Cong, R Widyasari… - ACM Transactions on …, 2024 - dl.acm.org
Since its introduction in November 2022, ChatGPT has rapidly gained popularity due to its
remarkable ability in language understanding and human-like responses. ChatGPT, based …

Devgpt: Studying developer-chatgpt conversations

T Xiao, C Treude, H Hata… - 2024 IEEE/ACM 21st …, 2024 - ieeexplore.ieee.org
This paper introduces DevGPT, a dataset curated to explore how software developers
interact with ChatGPT, a prominent large language model (LLM). The dataset encompasses …

Lilac: Log parsing using llms with adaptive parsing cache

Z Jiang, J Liu, Z Chen, Y Li, J Huang, Y Huo… - Proceedings of the …, 2024 - dl.acm.org
Log parsing transforms log messages into structured formats, serving as the prerequisite
step for various log analysis tasks. Although a variety of log parsing approaches have been …

Exploring parameter-efficient fine-tuning techniques for code generation with large language models

M Weyssow, X Zhou, K Kim, D Lo… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) possess impressive capabilities to generate meaningful
code snippets given natural language intents in zero-shot, ie, without the need for specific …

[HTML][HTML] Fine-tuning and prompt engineering for large language models-based code review automation

C Pornprasit, C Tantithamthavorn - Information and Software Technology, 2024 - Elsevier
Context: The rapid evolution of Large Language Models (LLMs) has sparked significant
interest in leveraging their capabilities for automating code review processes. Prior studies …

All languages matter: On the multilingual safety of large language models

W Wang, Z Tu, C Chen, Y Yuan, J Huang… - arXiv preprint arXiv …, 2023 - arxiv.org
Safety lies at the core of developing and deploying large language models (LLMs).
However, previous safety benchmarks only concern the safety in one language, eg the …

Evaluating and improving chatgpt for unit test generation

Z Yuan, M Liu, S Ding, K Wang, Y Chen… - Proceedings of the …, 2024 - dl.acm.org
Unit testing plays an essential role in detecting bugs in functionally-discrete program units
(eg, methods). Manually writing high-quality unit tests is time-consuming and laborious …