6 papers
Learning to Align Human Code Preferences
Xin Yin, Chao Ni, Xiaohu Yang
Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct…
Detecting LLM-generated Code with Subtle Modification by Adversarial Training
Xin Yin, Xinrui Li, Chao Ni +2
With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated develop…
Improving the Ability of Pre-trained Language Model by Imparting Large Language Model's Experience
Xin Yin, Chao Ni, Xiaodan Xu +2
Large Language Models (LLMs) and pre-trained Language Models (LMs) have achieved impressive success on many software engineering tasks (e.g., code completion and code generation).…
Enhancing LLM's Ability to Generate More Repository-Aware Unit Tests Through Precise Contextual Information Injection
Xin Yin, Chao Ni, Xinrui Li +3
Though many learning-based approaches have been proposed for unit test generation and achieved remarkable performance, they still have limitations in relying on task-specific datas…
What You See Is What You Get: Attention-based Self-guided Automatic Unit Test Generation
Xin Yin, Chao Ni, Xiaodan Xu +1
Software defects heavily affect software's functionalities and may cause huge losses. Recently, many AI-based approaches have been proposed to detect defects, which can be divided…
Distinguishing LLM-generated from Human-written Code by Contrastive Learning
Xiaodan Xu, Chao Ni, Xinrong Guo +4
Large language models (LLMs), such as ChatGPT released by OpenAI, have attracted significant attention from both industry and academia due to their demonstrated ability to generate…