Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning

Excerpt

arXiv:2606.07631v2 Announce Type: replace Abstract: Emergent misalignment (EM) occurs when narrow finetuning induces dangerous behavior outside the finetuning task. Detecting this shift through repeated behavioral evaluation is costly, motivating our checkpoint-level monitoring from internal representations. We define a fixed coordinate system from seven alignment-relevant activation directions and use it to track representational drift during LoRA finetuning of four open-source 7-9B language mo