Update README.md

README.md

@@ -131,7 +131,7 @@ We compare the performance of Granite 3.2-8b Instruct vs. Granite 3.2-8b LoRA ad
 - Joint Answerability-Faithfulness Score computed as:
     > = 1 (if model prediction = IDK/unanswerable ∩ ground truth = unanswerable)
 
-    > = RAGAS Faithfulness (if model prediction = IDK/answerable ∩ ground truth = answerable)
+    > = RAGAS Faithfulness (if model prediction = non-IDK/answerable ∩ ground truth = answerable)
     
     > = 0 (otherwise)