diff --git a/docs/source/advanced/pruning_quantization.rst b/docs/source/advanced/pruning_quantization.rst
index b9c8493b90..708a1ecb0d 100644
--- a/docs/source/advanced/pruning_quantization.rst
+++ b/docs/source/advanced/pruning_quantization.rst
@@ -35,7 +35,7 @@ This callback supports multiple pruning functions: pass any `torch.nn.utils.prun
     # set the amount to be the fraction of parameters to prune
     trainer = Trainer(callbacks=[ModelPruning("l1_unstructured", amount=0.5)])
 
-You can also perform iterative pruning, apply the `lottery ticket hypothesis <https://arxiv.org/pdf/1803.03635.pdf>`__, and more!
+You can also perform iterative pruning, apply the `lottery ticket hypothesis <https://arxiv.org/abs/1803.03635>`__, and more!
 
 .. code-block:: python
 
diff --git a/pytorch_lightning/callbacks/pruning.py b/pytorch_lightning/callbacks/pruning.py
index 70caaef8ed..83afaaf500 100644
--- a/pytorch_lightning/callbacks/pruning.py
+++ b/pytorch_lightning/callbacks/pruning.py
@@ -131,7 +131,7 @@ class ModelPruning(Callback):
             make_pruning_permanent: Whether to remove all reparametrization pre-hooks and apply masks
                 when training ends or the model is saved.
 
-            use_lottery_ticket_hypothesis: See `The lottery ticket hypothesis <https://arxiv.org/pdf/1803.03635.pdf>`_:
+            use_lottery_ticket_hypothesis: See `The lottery ticket hypothesis <https://arxiv.org/abs/1803.03635>`_:
 
                 - ``bool``. Whether to apply it or not.
                 - ``Callable[[epoch], bool]``. For dynamic values. Will be called every epoch.