iToT: An Interactive System for Customized Tree-of-Thought Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917765862916096 |
|---|---|
| author | Boyle, Alan Gupta, Isha Hönig, Sebastian Mautner, Lukas Amara, Kenza Cheng, Furui El-Assady, Mennatallah |
| author_facet | Boyle, Alan Gupta, Isha Hönig, Sebastian Mautner, Lukas Amara, Kenza Cheng, Furui El-Assady, Mennatallah |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00413 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | iToT: An Interactive System for Customized Tree-of-Thought Generation Boyle, Alan Gupta, Isha Hönig, Sebastian Mautner, Lukas Amara, Kenza Cheng, Furui El-Assady, Mennatallah Human-Computer Interaction 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. |
| title | iToT: An Interactive System for Customized Tree-of-Thought Generation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2409.00413 |