Randomness Is All You Need: Semantic Traversal of Problem-Solution Spaces with Large Language Models

Autor:	Sandholm, Thomas, Mukherjee, Sayandev, Huberman, Bernardo A.
Rok vydání:	2024
Předmět:	Computer Science - Human-Computer Interaction Computer Science - Artificial Intelligence Computer Science - Computers and Society
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.06053 Zobrazit plný text záznamu View this record from Arxiv