Update README.md

README.md

@@ -92,7 +92,7 @@ The model was pre-trained continuously on a single A10G GPU in an AWS instance f
 #### Possible Future Directions:
 
 1. Use a decoder-only model for pre-training and summarization.
-<br>As it seems the case when the span deleting tokens is not very large, the model learns to copy the token from the encoder to decoder generation.
+<br>As it seems the case when the span deleting tokens is not very large, the model learns to copy the token from the encoder context during Cross-attention to decoder generation.
 <br>Thus, hurts the performance of the Abstractive Summarization task.
 <br>This case is not present in the decoder-only model as all the predicted next token is not seen by the model at all.