Tree of Uncertain Thoughts Reasoning for Large Language Models

TL;DR

The paper introduces Tree of Uncertain Thoughts (TouT), a novel reasoning framework for large language models that incorporates local uncertainty quantification to improve decision-making in complex tasks.

Contribution

It presents TouT, which uses Monte Carlo Dropout to quantify local uncertainties and integrates this with global search, advancing reasoning capabilities of LLMs.

Findings

TouT outperforms Tree of Thoughts and chain-of-thought prompting in experiments.

TouT effectively quantifies local uncertainties to enhance reasoning accuracy.

Empirical results on planning tasks demonstrate TouT's superiority.

Abstract

While the recently introduced Tree of Thoughts (ToT) has heralded advancements in allowing Large Language Models (LLMs) to reason through foresight and backtracking for global decision-making, it has overlooked the inherent local uncertainties in intermediate decision points or "thoughts". These local uncertainties, intrinsic to LLMs given their potential for diverse responses, remain a significant concern in the reasoning process. Addressing this pivotal gap, we introduce the Tree of Uncertain Thoughts (TouT) - a reasoning framework tailored for LLMs. Our TouT effectively leverages Monte Carlo Dropout to quantify uncertainty scores associated with LLMs' diverse local responses at these intermediate steps. By marrying this local uncertainty quantification with global search algorithms, TouT enhances the model's precision in response generation. We substantiate our approach with rigorous experiments on two demanding planning tasks: Game of 24 and Mini Crosswords. The empirical evidence underscores TouT's superiority over both ToT and chain-of-thought prompting methods.