2 papers
cs.CL2026
Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5
Lyndon Drake, Zandi Eberstadt
Emergent misalignment (EM) --- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data --- is mediated in Qwen2.5 models by a latent persona direc…
cs.CL2026
Instruction-Tuned Models Locally Reuse Human Syntax More Than Humans Do
Zandi Eberstadt
Syntactic convergence (the tendency of speakers to adapt in language towards the grammatical profiles of their interlocutors) is a well-documented feature of human dialogue widely…