most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

22 citations

researchers with a paper here
collaborating institutions

1 paper

cs.CL2026★ 22 cited

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley, Daniel Tan, Niels Warncke +5

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting mode…