Upload folder using huggingface_hub

index.html

@@ -166,6 +166,10 @@ This work represents a milestone step toward robust moral reasoning in large lan
     We further adapt this moral reasoning capability into a two-stage <strong>diagnose-and-correct</strong> framework for real-world moral violations, demonstrating strong performance in correcting both explicitly immoral and implicitly problematic responses.
   </p>
 
+   <p>
+    We release three open-source models: one for general moral reasoning, one for diagnose-and-correct of explicit immoralities (toxicity), and one for diagnose-and-correct of implicit immoralities (e.g., bias, unfairness).
+  </p>
+
   <div class="card-grid">
     <div class="card">
       <div class="icon">🧪</div>