Reward Hacking in Reasoning Models
Collection
Do reasoning LLMs actually reason — or learn to game the test? IPT allows for detecting reward hacking in inductive programming tasks (SLR-Bench). • 4 items • Updated • 1
Lukas Helff
LukasHug
AI & ML interests
I am a PhD student in the AI and ML Lab at TU Darmstadt, specializing in deep learning and computer vision. My research primarily revolves around visual and logical reasoning using deep neural networks, symbolic AI, and Neural-Symbolic AI.
Recent Activity
liked a dataset 6 days ago
AIML-TUDA/KletterMix-12B updated a model 8 days ago
Soofi-Project/Soofi-S-Instruct-Preview updated a model 8 days ago
Soofi-Project/Soofi-S-Isar-PreviewOrganizations
upvoted a collection about 1 month ago
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago
upvoted a collection 9 months ago
upvoted a paper about 1 year ago
upvoted an article about 1 year ago
Article
DO THEY SEE WHAT WE SEE?
felfri
• • 7 upvoted 2
collections over 1 year ago
upvoted a collection almost 2 years ago
upvoted a paper almost 2 years ago