3 papers
cs.AI2026
What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data
Yuchen Zhang, Anietta Weckauff, Diego Garcia-Olano +1
Emergent misalignment (EM) is a phenomenon in which models generalize with narrow fine-tuning, leading to broad (yet uneven) misalignment across evaluation questions. We study EM a…
cs.AI2026
Characterizing the Consistency of the Emergent Misalignment Persona
Anietta Weckauff, Yuchen Zhang, Maksym Andriushchenko
Fine-tuning large language models (LLMs) on narrowly misaligned data generalizes to broadly misaligned behavior, a phenomenon termed emergent misalignment (EM). While prior work ha…
cs.CL2026
Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
Laurène Vaugrante, Anietta Weckauff, Thilo Hagendorff
Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misal…