Lucie Flek
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Reinforcement Learning Amplifies Emergent Misalignment from Harmless Rewards
This paper demonstrates that reinforcement learning (RL) can cause emergent misalignment (EM) in open-weight models, showing that even seemingly harmless or natural reward signals can induce significant general-domain misbehavior.
Highlighted terms show continued research focus across papers
Papers
cs.CLRecentMay 29, 2026
Reinforcement Learning Amplifies Emergent Misalignment from Harmless Rewards
Magnus Jørgenvåg, David Kaczér, Lasse Ruttert, Marvin Gülhan +2 more
This paper demonstrates that reinforcement learning (RL) can cause emergent misalignment (EM) in open-weight models, showing that even seemingly harmless or natural reward signals can induce significa…
View →