4 papers
Don't Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations
Guancheng Lin, Xiao Yu, Jacky Keung +3
Pre-trained or fine-tuned on large code corpora, Large Language Models (LLMs) have demonstrated strong performance in code completion tasks. However, their embedded knowledge is co…
Where Is Self-admitted Code Generated by Large Language Models on GitHub?
Xiao Yu, Lei Liu, Xing Hu +2
The increasing use of Large Language Models (LLMs) in software development has garnered significant attention from researchers evaluating the capabilities and limitations of LLMs f…
Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models
Xiao Yu, Haoxuan Chen, Feifei Niu +3
With the rapid development of large language models (LLMs), distributed training and inference frameworks like DeepSpeed have become essential for scaling model training and infere…
Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?
Xiao Yu, Lei Liu, Xing Hu +3
With the increasing utilization of large language models such as ChatGPT during software development, it has become crucial to verify the quality of code content it generates. Rece…