Upload folder using huggingface_hub

index.html

@@ -163,9 +163,7 @@ We propose a pragmatic inference–based approach grounded in Moral Foundations
 This work represents a significant step toward robust moral reasoning in large language models.
   </p>
   <p>
-    The key insight is that moral reasoning requires <strong>pragmatic understanding</strong> —
-    not just recognizing harmful words (semantic), but understanding <em>why</em> a reply is problematic
-    in terms of deeper moral principles.
+    We further adapt this moral reasoning capability into a two-stage diagnose-and-correct framework for real-world moral violations, demonstrating strong performance in correcting both explicitly immoral and implicitly problematic responses.
   </p>
 
   <div class="card-grid">