PopBlends: Strategies for Conceptual Blending with Large Language Models
This addresses the creative challenge of generating pop culture references for social media users, though it is incremental in combining existing methods.
The paper tackled the problem of automatically generating conceptual blends for pop culture references by developing PopBlends, a system that combines knowledge extraction and large language models. The result showed that users found twice as many blend suggestions with half the mental demand compared to without the system.
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.