Supermind Ideator: How Scaffolding Human-AI Collaboration Can Increase Creativity
Name
3643562.3672611.pdf
Size
1.65 MB
Format
Adobe PDF
Checksum (MD5)
ce38279f3e858c16d4582c11ff04c42f
Author(s)
Heyman, Jennifer
Rick, Steven
Giacomelli, Gianni
Wen, Haoran
Laubacher, Robert
Taubenslag, Nancy
Knicker, Max
Jeddi, Younes
Ragupathy, Pranav
Curhan, Jared
Date Issued
June 27, 2024
Publisher
ACM|Collective Intelligence Conference
Citation
Heyman, Jennifer, Rick, Steven, Giacomelli, Gianni, Wen, Haoran, Laubacher, Robert et al. 2024. "Supermind Ideator: How Scaffolding Human-AI Collaboration Can Increase Creativity."
Version
Final published version
Abstract
Previous efforts to support creative problem-solving have included (a) techniques such as brainstorming and design thinking to stimulate creative ideas, and (b) software tools to record and share these ideas. Now, generative AI technologies can suggest new ideas that might never have occurred to the users, and users can then select from these ideas or use them to stimulate even more ideas. To explore these possibilities, we developed a system called Supermind Ideator that uses a large language model (LLM) and adds prompts, fine tuning, and a specialized user interface in order to help users reformulate their problem statements and generate possible solutions. This provides scaffolding to guide users through a set of creative problem-solving techniques, including some techniques specifically intended to help generate innovative ideas about designing groups of people and/or computers (“superminds”). In an experimental study, we found that people using Supermind Ideator generated significantly more innovative ideas than those generated by people using ChatGPT or people working alone. Thus our results suggest that the benefits of using LLMs for creative problem-solving can be substantially enhanced by scaffolding designed specifically for this purpose.
Description
CI ’24, June 27–28, 2024, Boston, MA, USA
MIT Department
Sloan School of Management
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3643562.3672611
