Detecting outdated code element references in software repository documentation

WS Tan, M Wagner, C Treude - Empirical Software Engineering, 2024 - Springer
Outdated documentation is a pervasive problem in software development, preventing
effective use of software, and misleading users and developers alike. We posit that one …

TOGLL: Correct and Strong Test Oracle Generation with LLMs

SB Hossain, M Dwyer - arXiv preprint arXiv:2405.03786, 2024 - arxiv.org
Test oracles play a crucial role in software testing, enabling effective bug detection. Despite
initial promise, neural-based methods for automated test oracle generation often result in a …

Taking ASCII Drawings Seriously: How Programmers Diagram Code

D Hayatpur, B Hempel, K Chen, W Duan… - Proceedings of the CHI …, 2024 - dl.acm.org
Documentation in codebases facilitates knowledge transfer. But tools for programming are
largely text-based, and so developers resort to creating ASCII diagrams—graphical artifacts …

Lightweight precise automatic extraction of exception preconditions in java methods

D Marcilio, CA Furia - Empirical Software Engineering, 2024 - Springer
When a method throws an exception—its exception precondition—is a crucial element of the
method's documentation that clients should know to properly use it. Unfortunately …

Code Comment Inconsistency Detection Based on Confidence Learning

Z Xu, S Guo, Y Wang, R Chen, H Li… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Code comments are a crucial source of software documentation that captures various
aspects of the code. Such comments play a vital role in understanding the source code and …

Generating Exceptional Behavior Tests with Reasoning Augmented Large Language Models

J Zhang, Y Liu, P Nie, JJ Li, M Gligoric - arXiv preprint arXiv:2405.14619, 2024 - arxiv.org
Many popular programming languages, including C#, Java, and Python, support exceptions.
Exceptions are thrown during program execution if an unwanted event happens, eg, a …

[HTML][HTML] Translating meaning representations to behavioural interface specifications

IT Leong, R Barbosa - Journal of Systems and Software, 2024 - Elsevier
Higher-order logic can be used for meaning representation in natural language processing
to encode the semantic relationships in text. Alternatively, using a formal specification …

Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning

Y Mai, Z Gao, X Hu, L Bao, Y Liu, J Sun - arXiv preprint arXiv:2405.03509, 2024 - arxiv.org
Inspired by the great potential of Large Language Models (LLMs) for solving complex coding
tasks, in this paper, we propose a novel approach, named Code2API, to automatically …

LLM-Powered Test Case Generation for Detecting Tricky Bugs

K Liu, Y Liu, Z Chen, JM Zhang, Y Han, Y Ma… - arXiv preprint arXiv …, 2024 - arxiv.org
Conventional automated test generation tools struggle to generate test oracles and tricky
bug-revealing test inputs. Large Language Models (LLMs) can be prompted to produce test …

Are your comments outdated? Towards automatically detecting code-comment consistency

Y Huang, Y Chen, X Chen, X Zhou - arXiv preprint arXiv:2403.00251, 2024 - arxiv.org
In software development and maintenance, code comments can help developers
understand source code, and improve communication among developers. However …