Semantic Navigation for AI-assisted Ideation

TL;DR

This paper introduces a semantic navigation method for AI-assisted ideation that enhances idea exploration and generation quality, leading to increased engagement and more innovative outputs in a constrained domain.

Contribution

It proposes a novel semantic navigation approach supported by automated data filtering, improving idea exploration and generation quality over traditional prompt-based methods.

Findings

Semantic exploration is preferred over prompt-output interactions.

2.1x more generations are performed with semantic navigation.

Filtering input data improves generation quality and user experience.

Abstract

We present a novel AI-based ideation assistant and evaluate it in a user study with a group of innovators. The key contribution of our work is twofold: we propose a method of idea exploration in a constrained domain by means of LLM-supported semantic navigation of problem and solution spaces, and employ novel automated data input filtering to improve generations. We found that semantic exploration is preferred to the traditional prompt-output interactions, measured both in explicit survey rankings, and in terms of innovation assistant engagement, where 2.1x more generations were performed using semantic exploration. We also show that filtering input data with metrics such as relevancy, coherence and human alignment leads to improved generations in the same metrics as well as enhanced quality of experience among innovators.