4 papers
Anchor Attention, Small Cache: Code Generation with Large Language Models
Xiangyu Zhang, Yu Zhou, Guang Yang +2
The development of large language models (LLMs) has revolutionized automated code generation. However, their high demand of computation resources has hindered a broader deployment…
Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
Guang Yang, Yu Zhou, Xiang Chen +4
Code Language Models (CLMs), particularly those leveraging deep learning, have achieved significant success in code intelligence domain. However, the issue of security, particularl…
CodeScore-R: An Automated Robustness Metric for Assessing the FunctionalCorrectness of Code Synthesis
Guang Yang, Yu Zhou, Xiang Chen +1
Evaluation metrics are crucial in the field of code synthesis. Commonly used code evaluation metrics canbe classified into three types: match-based, semantic-based, and execution-b…
Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models
Guang Yang, Yu Zhou, Xiang Chen +3
Large Language Models (LLMs) have demonstrated remarkable potential in code generation. The integration of Chain of Thought (CoT) reasoning can further boost their performance. How…