update web

index.html

@@ -158,6 +158,36 @@ <h2 class="title is-3">Self-Play Fine-Tuning (SPIN)</h2>
   </div>
 </div>
 <!--/ SPIN. -->
+<!-- Results. -->
+<div class="columns is-centered">
+  <div class="column is-three-fifths">
+    <div class="content has-text-justified">
+      <p>
+        Our study focuses on fine-tuning LLMs without the need for additional human-annotated 
+        data beyond the fine-tuning dataset. Specifically, we consider following question: Can we empower a weak 
+        LLM to improve itself without acquiring additional human annotated data? In this paper, we answer this question affirmatively. 
+        Inspired by the success of self-play mechanisms in games, we propose
+        to convert a weak LLM to a strong one through the lens of self-play, where the model is enhanced
+        by playing against itself without requiring any direct supervision. 
+        In particular, we propose a novel fine-tuning method called Self-Play fIne-tuNing (SPIN), 
+        which begins from a supervised fine-tuned model. 
+      </p>
+    </div>
+  </div>
+</div>
+<!--/ Results. -->
+
+<!-- SPIN. -->
+<div class="columns is-centered">
+  <div class="column is-three-fifths">
+    <h2 class="title is-3"> </h2>
+    <h2 class="title is-3">Algorithm</h2>
+    <p align="center">
+      <img src="static/images/algorithm.png" height="300"/>
+    </p>
+  </div>
+</div>
+<!--/ SPIN. -->
 
 <!-- Results. -->
 <div class="columns is-centered">