deploy: MilaNLProc/mila-website-backend@cf60c36

404.html

@@ -595,6 +595,8 @@ <h1>Page not found</h1>
   <h2>Latest</h2>
   <ul>
 
+      <li><a href="/publication/2024-prism/">The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models</a></li>
+
       <li><a href="/publication/2024-divine-llamas-emotion-bias/">Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models</a></li>
 
       <li><a href="/publication/2024-compromesso/">Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models</a></li>
@@ -603,6 +605,8 @@ <h2>Latest</h2>
 
       <li><a href="/publication/2024-politicalcompass/">Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models</a></li>
 
+      <li><a href="/publication/2024-hate-geographies/">From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets</a></li>
+
       <li><a href="/publication/2024-xstest/">XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models</a></li>
 
       <li><a href="/publication/2024-dadit/">DADIT: A Dataset for Demographic Classification of Italian Twitter Users and a Comparison of Prediction Methods</a></li>
@@ -611,10 +615,6 @@ <h2>Latest</h2>
 
       <li><a href="/publication/2024-safetyllamas/">Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions</a></li>
 
-      <li><a href="/publication/2024-safetyprompts/">SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety </a></li>
-
-      <li><a href="/publication/2024-emotion-gender-stereotypes/">Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution</a></li>
-
   </ul>