8 citations · 19 across the 4 of their papers we have counts for
5 papers
BadEdit: Backdooring large language models by model editing
Yanzhou Li, Tianlin Li, Kangjie Chen +5
Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applie…
An Empirical Study on Noisy Label Learning for Program Understanding
Wenhan Wang, Yanzhou Li, Anran Li +3
Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challe…
Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs
Wei Ma, Zhihao Lin, Shangqing Liu +8
Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static seman…
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities
Wei Ma, Shangqing Liu, Mengjie Zhao +5
Past research has examined how well these models grasp code syntax, yet their understanding of code semantics still needs to be explored. We extensively analyze seven code models t…
Learning Program Representations with a Tree-Structured Transformer
Wenhan Wang, Kechi Zhang, Ge Li +4
Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to…