5 papers
Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation
Zhongxin Liu, Zhonghao Jiang, Zhifan Ye +3
LLM-based repository-level code generation aims to generate code using the context available in a software repository, requiring LLMs to reason over complex code dependencies. Due…
SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training
Keyu Liang, Haoye Wang, Yanfu Yan +2
Code search enhances developer productivity by enabling efficient code reuse. Current code search systems often use a retrieve-then-rerank pipeline, where rerankers focus on modeli…
FGIT: Fault-Guided Fine-Tuning for Code Generation
Lishui Fan, Zhongxin Liu, Haoye Wang +3
Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) so…
What Makes a Good TODO Comment?
Haoye Wang, Zhipeng Gao, Tingting Bi +4
Software development is a collaborative process that involves various interactions among individuals and teams. TODO comments in source code play a critical role in managing and co…
Instructive Code Retriever: Learn from Large Language Model's Feedback for Code Intelligence Tasks
Jiawei Lu, Haoye Wang, Zhongxin Liu +3
Recent studies proposed to leverage large language models (LLMs) with In-Context Learning (ICL) to handle code intelligence tasks without fine-tuning. ICL employs task instructions…