.png){kind=icon}
Return
How efficient is your clone? Evaluating LLM capabilities for runtime and memory-aware code selection
.png){kind=icon}
OA
AI
DOI：10.1016/j.jss.2026.112973.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Execution-free evaluation on CodeNet and CLBG across Python, Java, and C. • Code+feature prompts lift decoder LLMs more than encoder baselines. • LoRA yields selective gains; language–aspect effects remain context-dependent. • Top-1, MRR, and eGap reveal trade-offs beyond often-saturated Top-3.
Keywords:
Large Language Models (LLMs)
Execution-free code selection
Functionally equivalent implementations
Runtime-aware code analysis
Memory-aware code analysis
Code efficiency
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.1
Papers:
5.4K
Citations:
8.4K
Organization
Cited Papers
An empirical study on the impact of code duplication-aware refactoring practices on quality metrics
.png){kind=icon}
PREAI
ShareSaveHumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent
PREAI
ShareSave
ShareSaveShareSaveShareSave
View more