Update index.html

index.html

@@ -78,8 +78,12 @@ Exploring Refusal Loss Landscapes </title>
 </div>
 
 <h3 id="refusal-loss">Refusal Loss</h3>
-<p>Objectively, researchers utilize <strong>Calibration Metrics</strong> to measure the calibration error for a model, for example,
-Expected Calibration Error (ECE), Static Calibration Error (SCE), Adaptive Calibration Error (ACE), etc.</p>
+<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 <p>$T_\theta$</p> parameterized with $\theta$, we 
+  define the refusal loss function $\phi_\theta(x)$ for a given input user query $x$ as below:
+</p>
 
 <div class="container jailbreak-intro-sec">
 <div><img id="jailbreak-intro-img" src="images/metrics/intro-metric-example.png" /></div>