Towards an understanding of large language models in software engineering tasks

Z Zheng, K Ning, Q Zhong, J Chen, W Chen… - Empirical Software …, 2025 - Springer
Abstract Large Language Models (LLMs) have drawn widespread attention and research
due to their astounding performance in text generation and reasoning tasks. Derivative …

Pitfalls in language models for code intelligence: A taxonomy and survey

X She, Y Liu, Y Zhao, Y He, L Li… - arXiv preprint arXiv …, 2023 - arxiv.org
Modern language models (LMs) have been successfully employed in source code
generation and understanding, leading to a significant increase in research focused on …

Evaluating and explaining large language models for code using syntactic structures

DN Palacio, A Velasco, D Rodriguez-Cardenas… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) for code are a family of high-parameter, transformer-based
neural networks pre-trained on massive datasets of both natural and programming …

PTM-APIRec: Leveraging Pre-trained Models of Source Code in API Recommendation

Z Li, C Li, Z Tang, W Huang, J Ge, B Luo, V Ng… - ACM Transactions on …, 2024 - dl.acm.org
Recommending APIs is a practical and essential feature of IDEs. Improving the accuracy of
API recommendations is an effective way to improve coding efficiency. With the success of …

Improving cross-language code clone detection via code representation learning and graph neural networks

N Mehrotra, A Sharma, A Jindal… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Code clone detection is an important aspect of software development and maintenance. The
extensive research in this domain has helped reduce the complexity and increase the …

Transformers in source code generation: A comprehensive survey

H Ghaemi, Z Alizadehsani, A Shahraki… - Journal of Systems …, 2024 - Elsevier
Transformers have revolutionized natural language processing (NLP) and have had a huge
impact on automating tasks. Recently, transformers have led to the development of powerful …

[HTML][HTML] Enhancing Software Effort Estimation with Pre-Trained Word Embeddings: A Small-Dataset Solution for Accurate Story Point Prediction

I Atoum, AA Otoom - Electronics, 2024 - mdpi.com
Traditional software effort estimation methods, such as term frequency–inverse document
frequency (TF-IDF), are widely used due to their simplicity and interpretability. However, they …

IRC-CLVul: Cross-Programming-Language Vulnerability Detection with Intermediate Representations and Combined Features

T Lei, J Xue, Y Wang, Z Liu - Electronics, 2023 - mdpi.com
The most severe problem in cross-programming languages is feature extraction due to
different tokens in different programming languages. To solve this problem, we propose a …

CCCS: Contrastive Cross-Language Code Search Using Code Graph Information

L Kuang, Y Cheng, HH Gao - ACM Transactions on Asian and Low …, 2023 - dl.acm.org
Developers often search and reuse existing code snippets to improve software development
efficiency during software development. Currently, researchers have proposed many code …

[图书][B] Automatic Speech Recognition and Translation for Low Resource Languages

LA Kumar, DK Renuka, BR Chakravarthi, T Mandl - 2024 - books.google.com
AUTOMATIC SPEECH RECOGNITION and TRANSLATION for LOW-RESOURCE
LANGUAGES This book is a comprehensive exploration into the cutting-edge research …