activity
20232026
most citedMe, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers

Jan Dubiński, Jan Betley, Anna Sztyber-Betley +2

Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavior generalize to more egregio…