update app.py

app.py

@@ -149,12 +149,15 @@ demo = gr.Interface(
         gr.Plot(label="MLQA Dataset"),
         gr.Plot(label="ARCD Dataset")
     ],
-    title="Arabic Embedding Evaluation",
+    title="Evaluation of Arabic Matroyshka Embedding on Retrieval Tasks",
     description=(
-        "Evaluate your Sentence Transformer model on **Arabic retrieval tasks** using Matryoshka embeddings. "
-        "Compare performance across financial, long-context, and short-context datasets.\n\n"
-        "The evaluation uses **NDCG@10** to measure how well the model retrieves relevant contexts. "
-        "Embedding dimensions are reduced from 768 to 64."
+        "Evaluate your Embedding model or any Arabic Sentence Transformer model's performance on **context and question retrieval** for Arabic datasets for Enhancing RAG (Retrieval-Augmented Generation).\n"
+        "- **ARCD** evaluates short context retrieval performance.\n"
+        "- **MLQA Arabic** evaluates long context retrieval performance.\n"
+        "- **Arabic Financial Dataset** focuses on financial context retrieval.\n\n"
+        "**Evaluation Metric:**\n"
+        "The evaluation uses **NDCG@10** (Normalized Discounted Cumulative Gain), which measures how well the retrieved documents (contexts) match the query relevance.\n"
+        "Higher scores indicate better performance. Embedding dimensions are reduced from 768 to 64, evaluating how well the model performs with fewer dimensions."
     ),
     theme="default",
     live=False,