Update README.md

README.md

@@ -29,7 +29,7 @@ An example of its use and the code for its training is given in https://github.c
  
 # Uses
 
-The model is intended for usage as a discriminator in a text detoxification pipeline using the ParaGeDi approach (see [the paper](https://arxiv.org/abs/1911.00536) for more details). It can also be used for text generation conditional on toxic or non-toxic style, but  we do not know how to condition it on the things other than toxicity, so we do not recommend this usage. Another possible use is as a toxicity classifier (using the Bayes rule), but the model is not expected to perform better than e.g. a BERT-based standard classifier.
+The model is intended for usage as a discriminator in a text detoxification pipeline using the ParaGeDi approach (see [the paper](https://arxiv.org/abs/2109.08914) for more details). It can also be used for text generation conditional on toxic or non-toxic style, but  we do not know how to condition it on the things other than toxicity, so we do not recommend this usage. Another possible use is as a toxicity classifier (using the Bayes rule), but the model is not expected to perform better than e.g. a BERT-based standard classifier.
 
 # Bias, Risks, and Limitations
 The model inherits all the risks of its parent model, [gpt2-medium](https://huggingface.co/gpt2-medium/). It also inherits all the biases of the [Jigsaw dataset](https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge) on which it was fine-tuned. The model is intended to be conditional on style, but in fact it does not clearly separate the concepts of style and content, so it might regard some texts as toxic or safe based not on the style, but on their topics or keywords.