2 papers
cs.LG2026
How's it going? Reinforcement learning in language models recruits a functional welfare axis
Andy Q Han, David J. Chalmers, Pavel Izmailov
How does reinforcement learning shape a language model's internal representations? We present evidence that RL recruits a pre-existing representation of functional welfare: an esti…
cs.LG2026
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
Andy Han, Kristina Fujimoto, Avidan Shah +5
Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promi…