Mapping the Design Space of Interactions in Human-AI Text Co-creation Tasks
This work addresses the need for structured understanding of human-AI interactions in text co-creation for the generative AI and HCI research communities, but it is incremental as it primarily categorizes existing patterns.
The paper maps a spectrum of human-AI interaction patterns in text co-creation tasks, categorizing them into fixed-scope, independent creative, and complex interdependent tasks, and advocates for research focus on the more complex tasks requiring greater human involvement.
Large Language Models (LLMs) have demonstrated impressive text generation capabilities, prompting us to reconsider the future of human-AI co-creation and how humans interact with LLMs. In this paper, we present a spectrum of content generation tasks and their corresponding human-AI interaction patterns. These tasks include: 1) fixed-scope content curation tasks with minimal human-AI interactions, 2) independent creative tasks with precise human-AI interactions, and 3) complex and interdependent creative tasks with iterative human-AI interactions. We encourage the generative AI and HCI research communities to focus on the more complex and interdependent tasks, which require greater levels of human involvement.