18 lines
1.4 KiB
TeX
18 lines
1.4 KiB
TeX
% 摘要
|
||
\begin{center}
|
||
{\zihao{3}\textbf{毕业论文系统设计}}\par
|
||
{\zihao{-4}\songti 计算机科学与技术 \quad 专业 \quad 计科211（创） \quad 张三 \par
|
||
指导教师：李四教授}
|
||
\end{center}
|
||
|
||
% 中文摘要
|
||
\begin{onecolabstract}
|
||
\noindent{}\makebox[5em][l]{{\zihao{4}\textbf{摘要}}}{\songti \zihao{-4}本文研究了一种基于文档驱动的自适应编码大模型微调框架。该框架通过分析文档结构自动生成训练样本，实现了模型参数的高效优化。实验结果表明，该方法在多个NLP任务上取得了显著的性能提升，同时减少了人工标注的工作量。}\par
|
||
\noindent{}\makebox[5em][l]{{\zihao{4}\textbf{关键词}}}{\zihao{-4}\songti 关键词1；关键词2}\par
|
||
\end{onecolabstract}
|
||
|
||
% 英文摘要
|
||
\begin{onecolabstract}
|
||
\noindent{}\makebox[10em][l]{{\zihao{4} \textbf{ABSTRACT}}}{\zihao{-4}This paper proposes a document-driven adaptive fine-tuning framework for large coding models. By analyzing document structures to automatically generate training samples, the framework achieves efficient optimization of model parameters. Experimental results demonstrate significant performance improvements on multiple NLP tasks while reducing manual annotation workload.}\par
|
||
\noindent{}\makebox[10em][l]{{\zihao{4}\textbf{KEYWORDS}}}{\zihao{-4}Document-driven; Adaptive fine-tuning; Large language models; NLP tasks; Automatic annotation}\par
|
||
\end{onecolabstract} |