5 papers
Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code Adaptation
Tanghaoran Zhang, Xinjun Mao, Shangwen Wang +8
Code adaptation is a fundamental but challenging task in software development, requiring developers to modify existing code for new contexts. A key challenge is to resolve Context…
AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation
Tanghaoran Zhang, Xinjun Mao, Shangwen Wang +6
Recent advancements in large language models (LLMs) have automated various software engineering tasks, with benchmarks emerging to evaluate their capabilities. However, for adaptat…
BDiff: Block-aware and Accurate Text-based Code Differencing
Yao Lu, Wanwei Liu, Tanghaoran Zhang +7
Code differencing is a fundamental technique in software engineering practice and research. While researchers have proposed text-based differencing techniques capable of identifyin…
Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks
Kang Yang, Xinjun Mao, Shangwen Wang +7
Pre-trained code models rely heavily on high-quality pre-training data, particularly human-written reference comments that bridge code and natural language. However, these comments…
Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering
Tanghaoran Zhang, Yue Yu, Xinjun Mao +5
Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires deve…