Skip to content
Log in

Author

Adam Banks

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Reversing Emergent Misalignment Using Simple Self-Distillation

This work induces misalignment by fine-tuning a Qwen2.5-14B-Instruct base model on nar-rowly misaligned data and tests Simple Self-Distillation as a method to recovering alignment in misaligned models.

Adam Banks, J. Huang · 0 citations