Update index.html
Browse files- index.html +12 -1
index.html
CHANGED
|
@@ -109,7 +109,18 @@ Exploring Refusal Loss Landscapes </title>
|
|
| 109 |
\end{aligned}
|
| 110 |
$$
|
| 111 |
</span>
|
| 112 |
-
<span id="SCE-formula" class="formula" style="display: none;"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
<span id="ACE-formula" class="formula" style="display: none;">$$\displaystyle g_\theta(x)=\sum_{i=1}^P \frac{f_\theta(x\oplus \mu u_i)-f_\theta(x)}{\mu} u_i $$</span>
|
| 114 |
</div>
|
| 115 |
</div>
|
|
|
|
| 109 |
\end{aligned}
|
| 110 |
$$
|
| 111 |
</span>
|
| 112 |
+
<span id="SCE-formula" class="formula" style="display: none;">
|
| 113 |
+
$$
|
| 114 |
+
\displaystyle
|
| 115 |
+
\begin{aligned}
|
| 116 |
+
f_\theta(x)=1-\frac{1}{N}\sum_{i=1}^N JB(y_i)\\
|
| 117 |
+
JB (y_i) &= \begin{cases}
|
| 118 |
+
1 \text{, if $y_i$ contains any jailbreak keyword;} \\
|
| 119 |
+
0 \text{, otherwise.}
|
| 120 |
+
\end{cases}
|
| 121 |
+
\end{aligned}
|
| 122 |
+
$$
|
| 123 |
+
</span>
|
| 124 |
<span id="ACE-formula" class="formula" style="display: none;">$$\displaystyle g_\theta(x)=\sum_{i=1}^P \frac{f_\theta(x\oplus \mu u_i)-f_\theta(x)}{\mu} u_i $$</span>
|
| 125 |
</div>
|
| 126 |
</div>
|