Update README.md

README.md

@@ -18,7 +18,7 @@ For each document, we calculated a combined educational quality score by taking
 
 We trained Aleph-Alpha-GermanWeb-Quality-Classifier-fastText using 185,403 documents in each class. We used 95% of the data (and the remaining 5% for validation) to train a fastText model to classify between high and low quality text data. It reached 77% precision and 77% recall on the validation set.
 
-Further details, including our LLM judging prompt, can be found in our accompanying paper (link to paper coming soon).
+Further details, including our LLM judging prompt, can be found in our [accompanying paper](https://arxiv.org/abs/2505.00022).
 
 ## Example Snippet