Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment
Jason R. Brown, Patrick Leask, Lev McKinney
Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned beh…
cs.LG2026
Understanding Goal Generalisation in Sequential Reinforcement Learning
Jason Ross Brown, Edward James Young
Reinforcement learning agents often exhibit unintended goal-directed behaviour outside their training distribution, but we currently lack a principled understanding of how such age…