LLM-Based2 min read
Measuring Model-Specific Alignment Drift in LLM-Based Opinion Dynamics
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.
By Nata\v{s}a Djurdjevac Conrad, Sebastian Pokutta, Christof Sch\"uttearXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 4, 2026.
Comments
Sign in to join the discussion.