added paper link

README.md

@@ -17,7 +17,7 @@ The model can do one universal classification task: determine whether a hypothes
 This task format is based on the Natural Language Inference task (NLI).
 The task is so universal that any classification task can be reformulated into this task.
 
-A detailed description of how the model was trained and how it can be used is available in this paper: [link to be added]
+A detailed description of how the model was trained and how it can be used is available in this [paper](https://arxiv.org/pdf/2312.17543.pdf).
 
 ## Training data
 The model was trained on a mixture of __33 datasets and 387 classes__ that have been reformatted into this universal format.