Update README.md

README.md

@@ -187,7 +187,7 @@ Refer tables above
 
 #### Long Document Retrieval 
 
-This is very ambitious eval because we have not trained for long context, the max_len was 512 for all the models below.
+This is very ambitious eval because we have not trained for long context, the max_len was 512 for all the models below except BGE-M3 which had 8192 context and finetuned for long doc.
 
 <center>
 <img src="./ar_metrics_4.png" width=150%/>
@@ -197,11 +197,11 @@ This is very ambitious eval because we have not trained for long context, the ma
 
 #### X-lingual Retrieval 
 
-Almost all models below are monolingual arabic models so they have no notion of any other languages. But the below table shows how our model excels in cross-lingual scenarios owing to its deep multilingual understanding.
-This also explains its competitive performance when compared to models lot larger.
+Except BGE-M3 all are monolingual arabic models so they have no notion of any other languages. But the below table shows how our model understands arabic in context with other languages.
+This explains it's overall competitive performance when compared to models that are a LOT larger.
 
 <center>
-<img src="./ar_metrics_5.png" width=80%/>
+<img src="./ar_metrics_5.png" width=120%/>
   <b><p>Table 4: Detailed Arabic retrieval performance on the 3 X-lingual test set (measured by nDCG@10)</p></b>
 </center>