iToT: An Interactive System for Customized Tree-of-Thought Generation

TL;DR

iToT is an interactive, user-friendly system that enhances the Tree-of-Thoughts prompting method by enabling user interaction and visualization, thereby improving understanding and adaptability in problem-solving with language models.

Contribution

This paper introduces iToT, a generalized and interactive Tree-of-Thoughts system with a visual interface, addressing previous limitations of setup complexity and lack of user interaction.

Findings

iToT improves user understanding of model reasoning.

The system facilitates correction and extension of thoughts during problem-solving.

Case studies demonstrate enhanced performance in human-LLM co-writing tasks.

Abstract

As language models have become increasingly successful at a wide array of tasks, different prompt engineering methods have been developed alongside them in order to adapt these models to new tasks. One of them is Tree-of-Thoughts (ToT), a prompting strategy and framework for language model inference and problem-solving. It allows the model to explore multiple solution paths and select the best course of action, producing a tree-like structure of intermediate steps (i.e., thoughts). This method was shown to be effective for several problem types. However, the official implementation has a high barrier to usage as it requires setup overhead and incorporates task-specific problem templates which are difficult to generalize to new problem types. It also does not allow user interaction to improve or suggest new thoughts. We introduce iToT (interactive Tree-of-Thoughts), a generalized and interactive Tree of Thought prompting system. iToT allows users to explore each step of the model's problem-solving process as well as to correct and extend the model's thoughts. iToT revolves around a visual interface that facilitates simple and generic ToT usage and transparentizes the problem-solving process to users. This facilitates a better understanding of which thoughts and considerations lead to the model's final decision. Through three case studies, we demonstrate the usefulness of iToT in different human-LLM co-writing tasks.