diff --git a/spacy/cli/templates/quickstart_training.jinja b/spacy/cli/templates/quickstart_training.jinja
index b961ac892..ab61396d9 100644
--- a/spacy/cli/templates/quickstart_training.jinja
+++ b/spacy/cli/templates/quickstart_training.jinja
@@ -69,6 +69,7 @@ grad_factor = 1.0
 {% if "tagger" in components %}
 [components.tagger]
 factory = "tagger"
+label_smoothing = 0.05
 
 [components.tagger.model]
 @architectures = "spacy.Tagger.v2"
diff --git a/spacy/pipeline/tagger.pyx b/spacy/pipeline/tagger.pyx
index 86fbff911..5e4a5a5b7 100644
--- a/spacy/pipeline/tagger.pyx
+++ b/spacy/pipeline/tagger.pyx
@@ -45,7 +45,7 @@ DEFAULT_TAGGER_MODEL = Config().from_str(default_model_config)["model"]
 @Language.factory(
     "tagger",
     assigns=["token.tag"],
-    default_config={"model": DEFAULT_TAGGER_MODEL, "overwrite": False, "scorer": {"@scorers": "spacy.tagger_scorer.v1"}, "neg_prefix": "!", "label_smoothing": 0.05},
+    default_config={"model": DEFAULT_TAGGER_MODEL, "overwrite": False, "scorer": {"@scorers": "spacy.tagger_scorer.v1"}, "neg_prefix": "!", "label_smoothing": 0.0},
     default_score_weights={"tag_acc": 1.0},
 )
 def make_tagger(
diff --git a/spacy/tests/pipeline/test_tagger.py b/spacy/tests/pipeline/test_tagger.py
index de3602603..65c4cbe0a 100644
--- a/spacy/tests/pipeline/test_tagger.py
+++ b/spacy/tests/pipeline/test_tagger.py
@@ -70,10 +70,10 @@ PARTIAL_DATA = [
 def test_label_smoothing():
     util.fix_random_seed()
     nlp = Language()
-    tagger_no_ls = nlp.add_pipe(
-        "tagger", "no_label_smoothing", config=dict(label_smoothing=0.0)
+    tagger_no_ls = nlp.add_pipe("tagger", "no_label_smoothing")
+    tagger_ls = nlp.add_pipe(
+        "tagger", "label_smoothing", config=dict(label_smoothing=0.05)
     )
-    tagger_ls = nlp.add_pipe("tagger", "label_smoothing")
     train_examples = []
     losses = {}
     for tag in TAGS:
@@ -160,7 +160,7 @@ def test_no_data():
 def test_incomplete_data():
     # Test that the tagger works with incomplete information
     nlp = English()
-    nlp.add_pipe("tagger", config=dict(label_smoothing=0.0))
+    nlp.add_pipe("tagger")
     train_examples = []
     for t in PARTIAL_DATA:
         train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
@@ -180,7 +180,7 @@ def test_incomplete_data():
 def test_overfitting_IO():
     # Simple test to try and quickly overfit the tagger - ensuring the ML models work correctly
     nlp = English()
-    tagger = nlp.add_pipe("tagger", config=dict(label_smoothing=0.0))
+    tagger = nlp.add_pipe("tagger")
     train_examples = []
     for t in TRAIN_DATA:
         train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
diff --git a/spacy/tests/pipeline/test_tok2vec.py b/spacy/tests/pipeline/test_tok2vec.py
index 8fae0ef66..e423d9a19 100644
--- a/spacy/tests/pipeline/test_tok2vec.py
+++ b/spacy/tests/pipeline/test_tok2vec.py
@@ -115,7 +115,6 @@ cfg_string = """
 
     [components.tagger]
     factory = "tagger"
-    label_smoothing = 0.0
 
     [components.tagger.model]
     @architectures = "spacy.Tagger.v2"
diff --git a/website/docs/api/tagger.mdx b/website/docs/api/tagger.mdx
index e425a95d3..fdd234335 100644
--- a/website/docs/api/tagger.mdx
+++ b/website/docs/api/tagger.mdx
@@ -46,7 +46,7 @@ architectures and their arguments and hyperparameters.
 | `overwrite` <Tag variant="new">3.2</Tag>       | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~                                                                                                                                                                                                                              |
 | `scorer` <Tag variant="new">3.2</Tag>          | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attribute `"tag"`. ~~Optional[Callable]~~                                                                                                                                                            |
 | `neg_prefix` <Tag variant="new">3.2.1</Tag>    | The prefix used to specify incorrect tags while training. The tagger will learn not to predict exactly this tag. Defaults to `!`. ~~str~~                                                                                                                                                              |
-| `label_smoothing` <Tag variant="new">3.6</Tag> | Label smoothing factor. Defaults to `0.05`. ~~float~~                                                                                                                                                                                                                                   |
+| `label_smoothing` <Tag variant="new">3.6</Tag> | Label smoothing factor. Defaults to `0.0`. ~~float~~                                                                                                                                                                                                                                                   |
 
 ```python
 %%GITHUB_SPACY/spacy/pipeline/tagger.pyx