diff --git a/docs/mindformers/docs/source_en/appendix/conf_files.md b/docs/mindformers/docs/source_en/appendix/conf_files.md
index c09406c00852c35cac0c2efb7f692ced74dffdb0..551af07bb2ba8e696037263aa373b23b879a86eb 100644
--- a/docs/mindformers/docs/source_en/appendix/conf_files.md
+++ b/docs/mindformers/docs/source_en/appendix/conf_files.md
@@ -120,6 +120,7 @@ When starting model training, in addition to model-related parameters, you also
 | train_dataset.batch_size                    | The description is same as that of `runner_config.batch_size`                                                                                                                                                                       | int   |
 | train_dataset.input_columns                 | Set the input data columns for the training dataset                                                                                                                                                                                 | list  |
 | train_dataset.output_columns                | Set the output data columns for the training dataset                                                                                                                                                                                | list  |
+| train_dataset.construct_args_key         | Set whether the inputs to the dataset are passed into the model in lexicographical order, which is used when the order of the parameters passed to the model does not match the order of the inputs to the dataset  | list |
 | train_dataset.column_order                  | Set the order of the output data columns of the training dataset                                                                                                                                                                    | list  |
 | train_dataset.num_parallel_workers          | Set the number of processes that read the training dataset                                                                                                                                                                          | int   |
 | train_dataset.python_multiprocessing        | Enabling Python multi-process mode to improve data processing performance                                                                                                                                                           | bool  |
diff --git a/docs/mindformers/docs/source_zh_cn/appendix/conf_files.md b/docs/mindformers/docs/source_zh_cn/appendix/conf_files.md
index 3826259705b397112b6a1c418cbc9e9c406d5f70..ad591d79f1dc969a090bca1fe71fa42748a0e74a 100644
--- a/docs/mindformers/docs/source_zh_cn/appendix/conf_files.md
+++ b/docs/mindformers/docs/source_zh_cn/appendix/conf_files.md
@@ -120,6 +120,7 @@ Context配置主要用于指定[mindspore.set_context](https://www.mindspore.cn/
 | train_dataset.batch_size                    | 同`runner_config.batch_size`                                                                                                                                         | int   |
 | train_dataset.input_columns                 | 设置训练数据集输入的数据列                                                                                                                                                       | list  |
 | train_dataset.output_columns                | 设置训练数据集输出的数据列                                                                                                                                                       | list  |
+| train_dataset.construct_args_key         | 设置数据集的输入是否按照字典序传入模型，当模型的传参顺序和数据集输入的顺序不一致时使用该功能  | list |
 | train_dataset.column_order                  | 设置训练数据集输出数据列的顺序                                                                                                                                                     | list  |
 | train_dataset.num_parallel_workers          | 设置读取训练数据集的进程数                                                                                                                                                       | int   |
 | train_dataset.python_multiprocessing        | 是否开启Python多进程模式提升数据处理性能                                                                                                                                             | bool  |