Randomness Is All You Need: Semantic Traversal of Problem-Solution Spaces with Large Language Models
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_ | 1866909099317264384 |
|---|---|
| author | Sandholm, Thomas Mukherjee, Sayandev Huberman, Bernardo A. |
| author_facet | Sandholm, Thomas Mukherjee, Sayandev Huberman, Bernardo A. |
| contents | We present a novel approach to exploring innovation problem and solution domains using LLM fine-tuning with a custom idea database. By semantically traversing the bi-directional problem and solution tree at different temperature levels we achieve high diversity in solution edit distance while still remaining close to the original problem statement semantically. In addition to finding a variety of solutions to a given problem, this method can also be used to refine and clarify the original problem statement. As further validation of the approach, we implemented a proof-of-concept Slack bot to serve as an innovation assistant. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06053 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Randomness Is All You Need: Semantic Traversal of Problem-Solution Spaces with Large Language Models Sandholm, Thomas Mukherjee, Sayandev Huberman, Bernardo A. Human-Computer Interaction Artificial Intelligence Computers and Society We present a novel approach to exploring innovation problem and solution domains using LLM fine-tuning with a custom idea database. By semantically traversing the bi-directional problem and solution tree at different temperature levels we achieve high diversity in solution edit distance while still remaining close to the original problem statement semantically. In addition to finding a variety of solutions to a given problem, this method can also be used to refine and clarify the original problem statement. As further validation of the approach, we implemented a proof-of-concept Slack bot to serve as an innovation assistant. |
| title | Randomness Is All You Need: Semantic Traversal of Problem-Solution Spaces with Large Language Models |
| topic | Human-Computer Interaction Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2402.06053 |