Randomness Is All You Need: Semantic Traversal of Problem-Solution Spaces with Large Language Models
This work addresses the need for automated tools to generate diverse solutions and refine problem statements in innovation processes, though it appears incremental in applying existing LLM techniques to a specific domain.
The paper tackles the challenge of exploring innovation problem and solution spaces by using LLM fine-tuning with a custom idea database, achieving high diversity in solution edit distance while maintaining semantic closeness to the original problem. It also demonstrates a proof-of-concept Slack bot as an innovation assistant.
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.