Evaluating the role of `Constitutions' for learning from AI feedback
Paper
•
2411.10168
•
Published
•
5
Adam Mahdi
ammaox
AI & ML interests
LLMs, multimodal AI
Recent Activity
upvoted
a
paper
4 days ago
Evaluating the role of `Constitutions' for learning from AI feedback
authored
a paper
8 days ago
Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive
Toxicity Reduction
authored
a paper
8 days ago
Can sparse autoencoders be used to decompose and interpret steering
vectors?
Organizations
None yet