diff --git a/README.md b/README.md
index 9b89b2b..7ff9d0d 100644
--- a/README.md
+++ b/README.md
@@ -1472,13 +1472,13 @@ This will evaluate serialized documents including predicted annotations (see [In
 **Have a look into the [evaluate_documents.yaml](configs/evaluate_documents.yaml) config to see all available options**
 
 ```bash
-python src/evaluate_documents.py metric=f1 metric.layer=entities +dataset.data_dir=PATH/TO/DIR/WITH/SPLITS +dataset.document_type=TYPE/OF/DOCUMENT/IN/JSONL/FILE
+python src/evaluate_documents.py metric=f1 metric.layer=entities +dataset.data_dir=PATH/TO/DIR/WITH/SPLITS
 ```
 
 Note: By default, this utilizes the dataset provided by the
 [from_serialized_documents](configs/dataset/from_serialized_documents.yaml) configuration. This configuration is
 designed to facilitate the loading of serialized documents, as generated during the [Inference](#inference) step. It
-requires to set the parameters `document_type` and `data_dir` or `data_files`. If you want to use a different dataset,
+requires to set the parameter `data_dir`. If you want to use a different dataset,
 you can override the `dataset` parameter as usual with any existing dataset config, e.g `dataset=conll2003`. But
 calculating the F1 score on the bare `conll2003` dataset does not make much sense, because it does not contain any
 predictions. However, it could be used with statistical metrics such as