update

LeiLiLab · Dec 10, 2024 · 21424ed · 21424ed
1 parent b5ccb5c
commit 21424ed
Show file tree

Hide file tree

Showing 5 changed files with 9 additions and 2 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1 @@
+*.DS_Store
diff --git a/NeurIPS-tut-LLM-watermark-part-1.pdf b/NeurIPS-tut-LLM-watermark-part-1.pdf
diff --git a/NeurIPS-tut-LLM-watermark-part-2.pdf b/NeurIPS-tut-LLM-watermark-part-2.pdf
diff --git a/index.html b/index.html
@@ -187,13 +187,13 @@ <h2 class="title is-3">Schedule</h2>
     <div class="columns is-centered">
       <div class="column is-full-width">
 
-        <h3 class="title is-4">Part I: Introduction [<a href="ACL-tut-LLM-watermark-part-1.pdf">slides</a>]</h3>
+        <h3 class="title is-4">Part I: Introduction [<a href="NeurIPS-tut-LLM-watermark-part-1.pdf">slides</a>]</h3>
         <div class="content has-text-justified">
           <p><strong>Presenter:</strong> Xuandong Zhao</p>
           <p>This section provides the background for the tutorial, presenting the challenges posed by machine-written text and the potential ethical issues arising from Large Language Models (LLMs). We will introduce two primary approaches to addressing these issues: post-hoc detection and watermarking methods.</p>
         </div>
 
-        <h3 class="title is-4">Part II: Text Watermarking [<a href="ACL-tut-LLM-watermark-part-2.pdf">slides</a>]</h3>
+        <h3 class="title is-4">Part II: Text Watermarking [<a href="NeurIPS-tut-LLM-watermark-part-2.pdf">slides</a>]</h3>
         <div class="content has-text-justified">
           <p><strong>Presenter:</strong> Xuandong Zhao, Yu-Xiang Wang</p>
           <p>We delve into the process and evolution of watermarking for natural languages. We further explore watermarking methods specifically designed for Large Language Models. We will also cover the theoretical analysis of each watermarking method.</p>
@@ -249,6 +249,12 @@ <h3 class="title is-4">Part II: Text Watermarking [<a href="ACL-tut-LLM-watermar
                       Mark My Words: Analyzing and Evaluating Language Model Watermarks
                     </a>
                   </li>
+                  <li>
+                    PRC Watermark: Christ and Gunn. (2024) 
+                    <a href="https://arxiv.org/abs/2402.09370" target="_blank">
+                      Pseudorandom Error-Correcting Codes
+                    </a>
+                  </li>
                   <li>Other methods...</li>
               </ul>
               <li>Trade-offs among watermarking methods:

diff --git a/static/images/trade_off.png b/static/images/trade_off.png