diff --git a/develop/doc/api/v2/fluid/layers.html b/develop/doc/api/v2/fluid/layers.html
index e54c90c50b5fb421ecdc8c40bdb21ca05b887b3e..3c06ea26f7893a9d1c8ac5f899364605cc296297 100644
--- a/develop/doc/api/v2/fluid/layers.html
+++ b/develop/doc/api/v2/fluid/layers.html
@@ -424,8 +424,7 @@ Duplicable: False  Optional: False</td>
 <dd><p>Mul Operator.</p>
 <p>This operator is used to perform matrix multiplication for input $X$ and $Y$.</p>
 <p>The equation is:</p>
-<blockquote>
-<div>$$Out = X * Y$$</div></blockquote>
+<p>$$Out = X * Y$$</p>
 <p>Both the input $X$ and $Y$ can carry the LoD (Level of Details) information,
 or not. But the output only shares the LoD information with input $X$.</p>
 <table class="docutils field-list" frame="void" rules="none">
diff --git a/develop/doc/operators.json b/develop/doc/operators.json
index 4a953b5d8a393f1e9c90676695c4b0b9d34be2be..7c4a80c93746515f2e5fe685a68e922fd6a308e3 100644
--- a/develop/doc/operators.json
+++ b/develop/doc/operators.json
@@ -1145,7 +1145,7 @@
  } ] 
 },{
  "type" : "mul",
- "comment" : "\nMul Operator.\n\nThis operator is used to perform matrix multiplication for input $X$ and $Y$.\n\nThe equation is:\n\n    $$Out = X * Y$$\n\nBoth the input $X$ and $Y$ can carry the LoD (Level of Details) information,\nor not. But the output only shares the LoD information with input $X$.\n\n",
+ "comment" : "\nMul Operator.\n\nThis operator is used to perform matrix multiplication for input $X$ and $Y$.\n\nThe equation is:\n\n$$Out = X * Y$$\n\nBoth the input $X$ and $Y$ can carry the LoD (Level of Details) information,\nor not. But the output only shares the LoD information with input $X$.\n\n",
  "inputs" : [ 
  { 
    "name" : "X",
@@ -1358,7 +1358,7 @@
  } ] 
 },{
  "type" : "positive_negative_pair",
- "comment" : "\n        PositiveNegativePairOp can be used to evaluate Learning To Rank(LTR) \n        model performance. \n        Within some context, e.g. the \"query\", a LTR model generates scores\n        for a list of items, which gives a partial order of the items.\n        PositiveNegativePairOp takes a list of reference rank order \n        (Input(\"Label\")) and the model generated scores (Input(Score)) as \n        inputs and counts the pairs that ranked correctly and incorrectly.\n",
+ "comment" : "\nPositiveNegativePairOp can be used to evaluate Learning To Rank(LTR) model's\nperformance.\n\nWithin some context, e.g. the \"query\", a LTR model generates scores for a list\nof items, which gives a partial order of the items. PositiveNegativePairOp\ntakes a list of reference rank order (Input(\"Label\")) and the model generated\nscores (Input(Score)) as inputs and counts the pairs that ranked correctly\nand incorrectly.\n",
  "inputs" : [ 
  { 
    "name" : "Score",
diff --git a/develop/doc_cn/api/v2/fluid/layers.html b/develop/doc_cn/api/v2/fluid/layers.html
index c0e158edb2b03c78b68fce95fa50a8c589f7d024..cdecea77502f0fd0a7db9ced43a0f658a8c8f061 100644
--- a/develop/doc_cn/api/v2/fluid/layers.html
+++ b/develop/doc_cn/api/v2/fluid/layers.html
@@ -437,8 +437,7 @@ Duplicable: False  Optional: False</td>
 <dd><p>Mul Operator.</p>
 <p>This operator is used to perform matrix multiplication for input $X$ and $Y$.</p>
 <p>The equation is:</p>
-<blockquote>
-<div>$$Out = X * Y$$</div></blockquote>
+<p>$$Out = X * Y$$</p>
 <p>Both the input $X$ and $Y$ can carry the LoD (Level of Details) information,
 or not. But the output only shares the LoD information with input $X$.</p>
 <table class="docutils field-list" frame="void" rules="none">