Agents perform fewer inference steps from unobserved than observed variables in DAG belief updating, producing correlation neglect and iterated expectations failures.
Alternatives to B ayesian updating
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.
citing papers explorer
-
Limited belief propagation and contingent thinking
Agents perform fewer inference steps from unobserved than observed variables in DAG belief updating, producing correlation neglect and iterated expectations failures.
-
Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.