# PopBlends: Strategies for Conceptual Blending with Large Language Models

arXiv: https://arxiv.org/abs/2111.04920 · HTML: https://mlsanity.com/paper/2111.04920/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2021.

## Built on by (most cited first, 22 of 22)

- [PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement](https://mlsanity.com/paper/2403.04014/) (2024)
- [AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation](https://mlsanity.com/paper/2402.14978/) (2024)
- [ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles](https://mlsanity.com/paper/2310.15428/) (2023)
- [Generative Disco: Text-to-Video Generation for Music Visualization](https://mlsanity.com/paper/2304.08551/) (2023)
- [ReelFramer: Human-AI Co-Creation for News-to-Video Translation](https://mlsanity.com/paper/2304.09653/) (2023)
- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflow](https://mlsanity.com/paper/2402.09894/) (2024)
- [Tweetorial Hooks: Generative AI Tools to Motivate Science on Social Media](https://mlsanity.com/paper/2305.12265/) (2023)
- [OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMs](https://mlsanity.com/paper/2405.03901/) (2024)
- [PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows](https://mlsanity.com/paper/2310.15435/) (2023)
- [ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12](https://mlsanity.com/paper/2402.04975/) (2024)
- [Measuring Combinatorial Creativity in Large Language Models and Humans](https://mlsanity.com/paper/2509.21043/) (2025)
- [Leveraging Prompt-Based Large Language Models: Predicting Pandemic Health Decisions and Outcomes Through Social Media Language](https://mlsanity.com/paper/2403.00994/) (2024)
- [GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design](https://mlsanity.com/paper/2508.15227/) (2025)
- [Deconstructing the Veneer of Simplicity: Co-Designing Introductory Generative AI Workshops with Local Entrepreneurs](https://mlsanity.com/paper/2402.17082/) (2024)
- [Large Language Models to the Rescue: Reducing the Complexity in Scientific Workflow Development Using ChatGPT](https://mlsanity.com/paper/2311.01825/) (2023)
- ["With Great Power Comes Great Responsibility!": Student and Instructor Perspectives on the influence of LLMs on Undergraduate Engineering Education](https://mlsanity.com/paper/2309.10694/) (2023)
- [Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial](https://mlsanity.com/paper/2309.15074/) (2023)
- [An Artificial Intelligence Approach for Interpreting Creative Combinational Designs](https://mlsanity.com/paper/2405.04985/) (2024)
- [Blending Concepts with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2506.23630/) (2025)
- [Human-AI Schema Discovery and Application for Creative Problem Solving](https://mlsanity.com/paper/2508.05045/) (2025)

## Abstract (arXiv)

Pop culture is an important aspect of communication. On social media people often post pop culture reference images that connect an event, product or other entity to a pop culture domain. Creating these images is a creative challenge that requires finding a conceptual connection between the users' topic and a pop culture domain. In cognitive theory, this task is called conceptual blending. We present a system called PopBlends that automatically suggests conceptual blends. The system explores three approaches that involve both traditional knowledge extraction methods and large language models. Our annotation study shows that all three methods provide connections with similar accuracy, but with very different characteristics. Our user study shows that people found twice as many blend suggestions as they did without the system, and with half the mental demand. We discuss the advantages of combining large language models with knowledge bases for supporting divergent and convergent thinking.