arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.06053cs.HCcs.AIcs.CY
收藏

随机性即所需:利用大型语言模型对问题-解空间进行语义遍历

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

NextGen Systems(下一代系统公司);CableLabs(电缆实验室)

Thomas Sandholm, Sayandev Mukherjee, Bernardo A. Huberman

AI总结:

本文提出一种基于大型语言模型微调与创意数据库的方法,通过在不同温度下语义遍历双向问题-解树,在保持语义接近的同时生成多样化解,并用于问题澄清,以Slack机器人验证其可行性。

摘要:

我们提出了一种新颖的方法,利用大型语言模型微调与自定义创意数据库,来探索创新问题与解决方案领域。通过在双向的问题与解决方案树上,在不同温度水平下进行语义遍历,我们在解决方案编辑距离上实现了高多样性,同时仍能在语义上保持与原始问题陈述的接近。除了为给定问题找到多种解决方案外,该方法还可用于优化和澄清原始问题陈述。作为对该方法的进一步验证,我们实现了一个概念验证的Slack机器人,作为创新助手。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑