arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Peter Hase"" — arXiv2 Search
Showing 1–3 of 3 results
/ Date
/ Name
Apr 23, 2026
Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
Apr 15, 2024
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Jul 27, 2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback