Update README.md

README.md

@@ -3,5 +3,5 @@ license: apache-2.0
 ---
 We try to evaluate the LLM model performance in Indonesian.  
 There are many ways for calculate it, for example: BLEU, Perplexity, Human Eval, and GPT4 as Judge.  
-However, we use Perplexity as it was the fastest way for big evaluation dataset.  
-If you have any faster ways for calculating BLUE or any other metrics. Feel free to contribute in this repo.
+However, In our opinion, we use Perplexity as it was the fastest way for big evaluation dataset.  
+If you have any faster and easier ways for calculating BLUE or any other metrics. Feel free to contribute in this repo.