One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Generation of Humor

2025-01-20

AI Summary

Prior work lacks systematic evaluation of human-AI collaboration in culturally sensitive, humor-driven meme creation—a high-stakes creative domain demanding nuanced sociocultural awareness. Method: We conducted three controlled experiments (human-only, human-AI co-creation, AI-only) using an interactive GPT-4/Claude–powered interface and crowdsourced multidimensional subjective evaluation (creativity, humor, shareability), under a mixed-experimental design with statistical significance testing. Contribution/Results: Human-AI co-creation significantly increased output volume and reduced cognitive load versus human-only. While AI-only generated the highest average quality, among the top 20% outputs, human-only excelled in humor, whereas co-creation dominated in creativity and shareability—revealing a “productivity-quality paradox” wherein enhanced throughput does not guarantee superior quality. These findings provide empirical grounding for AI-augmented creative practice and inform interface design for culturally grounded generative systems.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Application Domains: Humanities & Computational Social Science

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Collaboration has been shown to enhance creativity leading to more innovative and effective outcomes While previous research has explored the abilities of Large Language Models LLMs to serve as cocreative partners in tasks like writing poetry or creating narratives the collaborative potential of LLMs in humorrich and culturally nuanced domains remains an open question To address this gap we conducted a user study to explore the potential of LLMs in cocreating memesa humordriven and culturally specific form of creative expression We conducted a user study with three groups of 50 participants each a humanonly group creating memes without AI assistance a humanAI collaboration group interacting with a stateoftheart LLM model and an AIonly group where the LLM autonomously generated memes We assessed the quality of the generated memes through crowdsourcing with each meme rated on creativity humor and shareability Our results showed that LLM assistance increased the number of ideas generated and reduced the effort participants felt However it did not improve the quality of the memes when humans were collaborated with LLM Interestingly memes created entirely by AI performed better than both humanonly and humanAI collaborative memes in all areas on average However when looking at the topperforming memes humancreated ones were better in humor while humanAI collaborations stood out in creativity and shareability These findings highlight the complexities of humanAI collaboration in creative tasks While AI can boost productivity and create content that appeals to a broad audience human creativity remains crucial for content that connects on a deeper level.

Problem

• Creative Collaboration
• Humor Perception
• Language Models

Innovation

• Large Language Models
• Humor Creativity
• Human-AI Collaboration