diff --git a/paper/latex/chapters/conclusion.tex b/paper/latex/chapters/conclusion.tex
index 01a7be4..2d727e1 100644
--- a/paper/latex/chapters/conclusion.tex
+++ b/paper/latex/chapters/conclusion.tex
@@ -1,8 +1,6 @@
 % 结论章节
 
-\section*{结论}
-\newcounter{结论编号}   %创建一个计数器，这个计数用于给结论章节编号                     
-\setcounter{结论编号}{\value{section}} %计数器就像变量一样
-\addtocounter{结论编号}{1}
-\addcontentsline{toc}{section}{\arabic{结论编号}\quad 结论\tiny{\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad.\quad}}
+\section{结论}
+
+
 本文提出的文档驱动自适应编码框架有效解决了大模型微调中的样本利用率问题，实验结果表明该方法在多个NLP任务上性能提升显著。
\ No newline at end of file