29 citations · 37 across the 5 of their papers we have counts for
4 papers · 1 filter
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…
Gauss-Newton Unlearning for the LLM Era
Lev McKinney, Anvith Thudi, Juhan Bae +4
Standard large language model training can create models that produce outputs their trainer deems unacceptable in deployment. The probability of these outputs can be reduced using…
Eliciting Latent Predictions from Transformers with the Tuned Lens
Nora Belrose, Igor Ostrovsky, Lev McKinney +5
We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for…
On The Fragility of Learned Reward Functions
Lev McKinney, Yawen Duan, David Krueger +1
Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and…