Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

TL;DR

This paper introduces Uncertainty of Thoughts (UoT), a novel algorithm that enables large language models to actively seek information through effective questioning by simulating future scenarios and optimizing question selection.

Contribution

UoT combines uncertainty-aware simulation, information gain-based rewards, and a reward propagation scheme to improve LLMs' ability to seek information actively.

Findings

38.1% improvement in task success rate

Enhanced efficiency in information seeking

Effective across multiple applications and models

Abstract

In the face of uncertainty, the ability to *seek information* is of fundamental importance. In many practical applications, such as medical diagnosis and troubleshooting, the information needed to solve the task is not initially given and has to be actively sought by asking follow-up questions (for example, a doctor asking a patient for more details about their symptoms). In this work, we introduce Uncertainty of Thoughts (UoT), an algorithm to augment large language models with the ability to actively seek information by asking effective questions. UoT combines 1) an *uncertainty-aware simulation approach* which enables the model to simulate possible future scenarios and how likely they are to occur, 2) *uncertainty-based rewards* motivated by information gain which incentivizes the model to seek information, and 3) a *reward propagation scheme* to select the optimal question to ask in a way that maximizes the expected reward. In experiments on medical diagnosis, troubleshooting, and the `20 Questions` game, UoT achieves an average performance improvement of 38.1% in the rate of successful task completion across multiple LLMs compared with direct prompting and also improves efficiency (i.e., the number of questions needed to complete the task). Our code has been released [here](https://github.com/zhiyuanhubj/UoT)