Update app.py

app.py

@@ -286,11 +286,11 @@ Dingli Yu* Simran Kaur* Arushi Gupta* Jonah Brown-Cohen† Anirudh Goyal† Sanj
 
 ### This is a demonstration of the Skill-Mix evaluation. 
 
-Paper link: [place holder]{www.arxiv.org}
+Paper link: [coming soon](www.arxiv.org)
 
 ### Samples are generated using 10% of the full set of skills and topics. Click the second tab for comparison between two generations.
 
-Coming soon: generation by models other than the GPT family and LLaMA-2 family; grading by LLaMA-2.
+Coming soon: generation by more models; grading by LLaMA-2.
 """
         )