Measuring Model-Specific Alignment Drift in LLM-Based Opinion Dynamics

arXiv:2611.03980v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as synthetic participants in opinion-dynamics experiments, often assuming that an agent's behaviour is fully determined by its prompt. We test this assumption with a framework in which LLM agents

arXiv cs.AIMittwoch 06:00 · 04.11.1 Min. Lesezeit