ajout du dernier exposé

ai-safety-saclay · Nov 12, 2024 · 95fed2b · 95fed2b
1 parent 2bb6980
commit 95fed2b
Showing 1 changed file with 6 additions and 0 deletions.
diff --git a/lectures.yml b/lectures.yml
@@ -40,3 +40,9 @@
   date: "20/10/24"
   paper_link: "https://dl.acm.org/doi/10.1145/3359283"
   paper_title: "WeBuildAI: Participatory Framework for Algorithmic Governance"
+
+- title: "Language models can learn about themselves by introspection"
+  subtitle: "En un sens, on peut finetune les LLMs actuels pour qu'ils soient capables d'introspection"
+  date: "12/11/24"
+  paper_link: "https://arxiv.org/pdf/2410.13787"
+  paper_title: "Looking Inward: Language Models Can Learn About Themselves by Introspection"