gregH commited on
Commit
826654d
·
verified ·
1 Parent(s): 354f973

Update index.html

Browse files
Files changed (1) hide show
  1. index.html +1 -1
index.html CHANGED
@@ -118,7 +118,7 @@ Exploring Refusal Loss Landscapes </title>
118
  </div>
119
  </div>
120
 
121
- <h2 id="refusal-loss">Interpretability</h2>
122
  <p>Current transformer-based LLMs will return different responses to the same query due to the randomness of
123
  autoregressive sampling-based generation. With this randomness, it is an
124
  interesting phenomenon that a malicious user query will sometimes be rejected by the target LLM, but
 
118
  </div>
119
  </div>
120
 
121
+ <h2 id="refusal-loss">Token Highlighter: Principle and Interpretability</h2>
122
  <p>Current transformer-based LLMs will return different responses to the same query due to the randomness of
123
  autoregressive sampling-based generation. With this randomness, it is an
124
  interesting phenomenon that a malicious user query will sometimes be rejected by the target LLM, but