Update README.md

README.md

@@ -177,7 +177,7 @@ The below numbers are with mDPR model, but miniDense_arabic_v1 should give a eve
 
 *Note: MIRACL paper shows a different (higher) value for BM25 Arabic, So we are taking that value from BGE-M3 paper, rest all are form the MIRACL paper.*
 
-# MTEB numbers:
+# MTEB Retrieval numbers:
 MTEB is a general purpose embedding evaluation benchmark covering wide range of tasks, but miniDense models (like BGE-M3) are predominantly tuned for retireval tasks aimed at search & IR based usecases.
 So it makes sense to evaluate our models in retrieval slice of the MTEB benchmark.
 
@@ -185,13 +185,22 @@ So it makes sense to evaluate our models in retrieval slice of the MTEB benchmar
 
 Refer tables above 
 
+#### Sadeem Question Retrieval 
+
+<center>
+<img src="./ar_metrics_6.png" width=150%/>
+  <b><p>Table 3: Detailed Arabic retrieval performance on the SadeemQA eval set (measured by nDCG@10)</p></b>
+</center>
+
+
+
 #### 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 except BGE-M3 which had 8192 context and finetuned for long doc.
 
 <center>
 <img src="./ar_metrics_4.png" width=150%/>
-  <b><p>Table 3: Detailed Arabic retrieval performance on the MultiLongDoc dev set (measured by nDCG@10)</p></b>
+  <b><p>Table 4: Detailed Arabic retrieval performance on the MultiLongDoc dev set (measured by nDCG@10)</p></b>
 </center>
 
 
@@ -202,7 +211,7 @@ This explains it's overall competitive performance when compared to models that
 
 <center>
 <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>
+  <b><p>Table 5: Detailed Arabic retrieval performance on the 3 X-lingual test set (measured by nDCG@10)</p></b>
 </center>
 
 <br/>