
Epistemic uncertainty plays a fundamental role in decision-making tasks with Large Language Models, and actively incorporating it through Thompson Sampling policies can significantly improve performance compared to greedy approaches.


coremsg

leveraging-epistemic-uncertainty-for-improved-decision-making-with-large-language-models-in-contextual-bandits


Leveraging Epistemic Uncertainty for Improved Decision-Making with Large Language Models in Contextual Bandits
