diff --git a/optimum/neuron/generation/token_selector.py b/optimum/neuron/generation/token_selector.py
index 62a95fb1c..2d64d03fc 100644
--- a/optimum/neuron/generation/token_selector.py
+++ b/optimum/neuron/generation/token_selector.py
@@ -71,7 +71,7 @@ def create(
                 The model provides the internal helpers allowing to select the logits processors and stopping criterias.
             max_seq_length (`int`):
                 The maximum number of input + generated tokens for this model. It depends on the model compilation parameters.
-            stopping_criteria (`Optional[transformers.generation.StoppingCriteriaList]):
+            stopping_criteria (`Optional[transformers.generation.StoppingCriteriaList], defaults to `None`):
                 Custom stopping criteria that complement the default stopping criteria built from arguments and a
                 generation config.
         Return:
diff --git a/optimum/neuron/modeling.py b/optimum/neuron/modeling.py
index 5b6944ea5..9f37f9b9e 100644
--- a/optimum/neuron/modeling.py
+++ b/optimum/neuron/modeling.py
@@ -749,7 +749,7 @@ def generate(
                 priority: 1) from the `generation_config.json` model file, if it exists; 2) from the model
                 configuration. Please note that unspecified parameters will inherit [`~transformers.generation.GenerationConfig`]'s
                 default values, whose documentation should be checked to parameterize generation.
-            stopping_criteria (`Optional[transformers.generation.StoppingCriteriaList]):
+            stopping_criteria (`Optional[transformers.generation.StoppingCriteriaList], defaults to `None`):
                 Custom stopping criteria that complement the default stopping criteria built from arguments and a
                 generation config.