Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents
Bayesian Chronicle Agents is introduced, a minimal belief layer separating what an agent believes from how it speaks, and it is shown that prescribed $\kappa$ remains recoverable after the language round-trip, with perfect rank-order recovery across all four models.
Hafsa Akbar, Daniel Platnick, Marjan Alirezaie et al.
· 0 citations