Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Rapid AIdeation: Generating Ideas With the Self and in Collaboration With Large Language Models

Gionnieve Lim, Simon T. Perrault

TL;DR

It is found that the large language model (LLM) produced a greater variety of ideas that were of high quality, though not necessarily of higher quality than human-generated ideas.

Abstract

Generative artificial intelligence (GenAI) can rapidly produce large and diverse volumes of content. This lends to it a quality of creativity which can be empowering in the early stages of design. In seeking to understand how creative ways to address practical issues can be conceived between humans and GenAI, we conducted a rapid ideation workshop with 21 participants where they used a large language model (LLM) to brainstorm potential solutions and evaluate them. We found that the LLM produced a greater variety of ideas that were of high quality, though not necessarily of higher quality than human-generated ideas. Participants typically prompted in a straightforward manner with concise instructions. We also observed two collaborative dynamics with the LLM fulfilling a consulting role or an assisting role depending on the goals of the users. Notably, we observed an atypical anti-collaboration dynamic where participants used an antagonistic approach to prompt the LLM.

Rapid AIdeation: Generating Ideas With the Self and in Collaboration With Large Language Models

TL;DR

It is found that the large language model (LLM) produced a greater variety of ideas that were of high quality, though not necessarily of higher quality than human-generated ideas.

Abstract

Generative artificial intelligence (GenAI) can rapidly produce large and diverse volumes of content. This lends to it a quality of creativity which can be empowering in the early stages of design. In seeking to understand how creative ways to address practical issues can be conceived between humans and GenAI, we conducted a rapid ideation workshop with 21 participants where they used a large language model (LLM) to brainstorm potential solutions and evaluate them. We found that the LLM produced a greater variety of ideas that were of high quality, though not necessarily of higher quality than human-generated ideas. Participants typically prompted in a straightforward manner with concise instructions. We also observed two collaborative dynamics with the LLM fulfilling a consulting role or an assisting role depending on the goals of the users. Notably, we observed an atypical anti-collaboration dynamic where participants used an antagonistic approach to prompt the LLM.
Paper Structure (24 sections, 6 figures, 1 table)

This paper contains 24 sections, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Brainstorming and the Creative Process
  4. Co-Creation and Collaboration with LLMs
  5. Method
  6. Workshop
  7. Participants
  8. Analysis
  9. Results
  10. RQ1: Which ideation process produces more unique ideas?
  11. RQ2: Which ideation process produces better quality ideas?
  12. RQ3: How do users prompt ChatGPT to obtain their desired outcomes?
  13. Requests
  14. Prompting behavior
  15. Discussion
  16. ...and 9 more sections

Figures (6)

  • Figure 1: Phases of the workshop
  • Figure 2: Instructions for the workshop activities
  • Figure 3: Content analysis of post-its from the Self Ideation phase for the Misinformation issue
  • Figure 4: Content analysis of post-its from the Co-GPT Ideation phase for the Misinformation issue
  • Figure 5: Content analysis of post-its from the Self Ideation phase for the Hallucination issue
  • ...and 1 more figures