Using Large Language Models for Idea Generation in Innovation

2026-07-29

AI Summary

This study investigates the performance of large language models—specifically GPT-4—in generating new product ideas, with a focus on comparing the quality, novelty, and diversity of AI-generated concepts against those produced by humans. The authors evaluate 50-dollar-or-less product ideas targeting college students, generated both by undergraduate participants and GPT-4 under zero-shot and few-shot prompting conditions. Using a multimodal assessment framework combining market surveys, text mining, and expert human ratings, the findings reveal that AI-generated ideas elicit higher average purchase intent and are seven times more likely to yield top-tier concepts than human-generated ones, highlighting AI’s high-output potential in early-stage innovation. However, AI outputs exhibit lower novelty and greater semantic similarity among ideas, particularly under few-shot settings. This work provides the first systematic quantification of AI’s dual advantage in both average idea quality and the proportion of high-performing concepts.

Abstract

This research evaluates the efficacy of large language models (LLMs) in generating new product ideas. To do so, we compare three pools of ideas for new products targeted toward college students and priced at 50 dollars or less. The first pool of ideas was created by university students in a product design course before the availability of LLMs. The second and third pools of ideas were generated by GPT-4 from OpenAI using zero-shot and few-shot prompting, respectively. We evaluated idea quality using standard market research techniques to predict average purchase intent probability. We used text mining to assess idea similarity and human raters to evaluate idea novelty. We find that AI-generated ideas outperform human-generated ideas in terms of average purchase intent, with few-shot prompting yielding slightly higher intent than zero-shot prompting. However, AI-generated ideas are perceived as less novel and exhibit higher pairwise similarity, particularly with few-shot prompting, indicating a less diverse solution landscape. When focusing on the quality of the best ideas rather than the average ideas, we find that AI-generated ideas are seven times more likely to rank among the top 10 percent of ideas, demonstrating a significant advantage over human-generated ideas. We propose that this seven-to-one advantage is a conservative estimate because it does not account for the greater productivity of AI. Our findings suggest that despite some drawbacks, AI creativity presents a substantial benefit in generating high-quality ideas for new product development.

Problem

• Large Language Models
• Idea Generation
• Innovation
• Product Development
• Creativity

Innovation

• large language models
• idea generation
• few-shot prompting
• purchase intent
• creativity evaluation