发表机构
University of Texas at Arlington; Microsoft（阿灵顿得克萨斯大学; 微软）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出ShikumiMiner静态分析框架，结合AST与CFG特征挖掘C++本地LLM代码库的重复实现模式，分析10个GitHub开源库并分类函数，为LLM应用开发者提供参考。
AI 中文摘要
大型语言模型（LLM）通过理解、分析、总结和生成内容，为现代世界的创新铺平了道路。目前，开源代码库中有数千个由工程师开发的LLM项目，但这些LLM项目是否存在潜在模式仍是一个问题。探索这些潜在模式将为开发LLM项目的开发者提供新的视角。本文提出了ShikumiMiner，这是一个结合抽象语法树（AST）和控制流图（CFG）特征的静态分析框架，用于检测和比较C++本地LLM代码库中重复出现的实现模式。我们分析了10个GitHub开源代码库，并使用多标签随机森林模型将函数分为7个特定研究类别。研究这些模式可为旨在设计LLM应用的开发者提供有用的见解。
英文摘要
Large language models are paving the way towards innovation by understanding, analyzing, summarizing and generating content in the modern world. Currently there are thousands of LLM projects developed by engineers in open-source repositories. However, whether these LLM projects have underlying patterns or not remains a question. Exploring these underlying patterns will give new dimensions to the developers who aim to develop these LLM projects. In this paper, we propose ShikumiMiner, a static-analysis framework that combines Abstract Syntax Tree (AST) and Control Flow Graph (CFG) features to detect and compare recurring implementation patterns in C++ local LLM codebases. We analyze ten GitHub open-source repositories and classify functions into seven study-specific categories using a multi-label Random Forest model. Studying these patterns can provide useful insights for developers aiming to design LLM applications.
