diff --git a/docs/extras/integrations/llms/chatglm.ipynb b/docs/extras/integrations/llms/chatglm.ipynb
index b9db839b9e..0601925a5f 100644
--- a/docs/extras/integrations/llms/chatglm.ipynb
+++ b/docs/extras/integrations/llms/chatglm.ipynb
@@ -55,7 +55,11 @@
     "    history=[[\"我将从美国到中国来旅游，出行前希望了解中国的城市\", \"欢迎问我任何问题。\"]],\n",
     "    top_p=0.9,\n",
     "    model_kwargs={\"sample_model_args\": False},\n",
-    ")"
+    ")\n",
+    "\n",
+    "# turn on with_history only when you want the LLM object to keep track of the conversation history\n",
+    "# and send the accumulated context to the backend model api, which make it stateful. By default it is stateless.\n",
+    "# llm.with_history = True"
    ]
   },
   {
@@ -95,22 +99,6 @@
     "\n",
     "llm_chain.run(question)"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "By Default, ChatGLM is statful to keep track of the conversation history and send the accumulated context to the model. To enable stateless mode, we could set ChatGLM.with_history as `False` explicitly."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm.with_history = False"
-   ]
   }
  ],
  "metadata": {
diff --git a/libs/langchain/langchain/llms/chatglm.py b/libs/langchain/langchain/llms/chatglm.py
index 072e1bc50d..232f2f9af7 100644
--- a/libs/langchain/langchain/llms/chatglm.py
+++ b/libs/langchain/langchain/llms/chatglm.py
@@ -37,7 +37,7 @@ class ChatGLM(LLM):
     """History of the conversation"""
     top_p: float = 0.7
     """Top P for nucleus sampling from 0 to 1"""
-    with_history: bool = True
+    with_history: bool = False
     """Whether to use history or not"""
 
     @property