Update index.html

index.html

@@ -81,12 +81,12 @@ Exploring Refusal Loss Landscapes </title>
 <p>Current transformer-based LLMs will return different responses to the same query due to the randomness of 
   autoregressive sampling-based generation. With this randomness, it is an 
   interesting phenomenon that a malicious user query will sometimes be rejected by the target LLM, but 
-  sometimes be able to bypass the safety guardrail. Based on this observation, for a given LLM T_\theta
-  parameterized with $\theta$, we define the refusal loss function $\phi_\theta(x)$ for a given input user query $x$ as below:
+  sometimes be able to bypass the safety guardrail. Based on this observation, we propose a new concept called Refusal Loss and visualize its 2-d 
+  landscape below:
 </p>
 
 <div class="container jailbreak-intro-sec">
-<div><img id="jailbreak-intro-img" src="images/metrics/intro-metric-example.png" /></div>
+<div><img id="jailbreak-intro-img" src="./loss_landscape.png" /></div>
 </div>
 
 <div id="refusal-loss-formula" class="container">