Reinforcement learning recruits rather than creates a functional welfare axis in language models, as reward and punishment vectors from a maze task generalize to unrelated settings and appear in pretrain-only models.
arXiv preprint arXiv:2602.02132 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Suppressing one refusal neuron or amplifying one concept neuron bypasses safety alignment in LLMs from 1.7B to 70B parameters without training or prompt engineering.
citing papers explorer
-
How's it going? Reinforcement learning in language models recruits a functional welfare axis
Reinforcement learning recruits rather than creates a functional welfare axis in language models, as reward and punishment vectors from a maze task generalize to unrelated settings and appear in pretrain-only models.
-
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Suppressing one refusal neuron or amplifying one concept neuron bypasses safety alignment in LLMs from 1.7B to 70B parameters without training or prompt engineering.