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

Alan Boyle1 + Isha Gupta1 + Sebastian Hönig1 + Lukas Mautner1 + Kenza Amara1 Furui Cheng1 Mennatallah El-Assady1
1ETH Zurich     +equal contribution

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 two case studies, we demonstrate the usefulness of iToT in different human-LLM co-writing tasks.

Preprint Demo

@misc{bghm2024itot,
  title={{iToT}: An Interactive System for Customized Tree-of-Thought Generation},
  author={Boyle, Alan and Gupta, Isha and Hönig, Sebastian and Mautner, Lukas and Amara, Kenza and El-Assady, Mennatallah},
  year={2024},
  url={https://arxiv.org/abs/2409.00413}
  note={ETH Zürich}
}