Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs

• Main Authors: Zhang, Lei, Li, Yunshui, Li, Jiaming, Xia, Xiaobo, Yang, Jiaxi, Luo, Run, Wang, Minzheng, Chen, Longze, Liu, Junhao, Yang, Min
• Format: Journal Article
• Language: English
• Published: 26.06.2024
• Subjects: Computer Science - Computation and Language

Some recently developed code large language models (Code LLMs) have been pre-trained on repository-level code data (Repo-Code LLMs), enabling these models to recognize repository structures and utilize cross-file information for code completion. However, in real-world development scenarios, simply c...