Intent Tagging: Exploring Micro-Prompting Interactions for Supporting Granular Human-GenAI Co-Creation Workflows

Abstract

Despite Generative AI (GenAI) systems' potential for enhancing content creation, users often struggle to effectively integrate GenAI into their creative workflows. Core challenges include misalignment of AI-generated content with user intentions (intent elicitation and alignment), user uncertainty around how to best communicate their intents to the AI system (prompt formulation), and insufficient flexibility of AI systems to support diverse creative workflows (workflow flexibility). Motivated by these challenges, we created IntentTagger: a system for slide creation based on the notion of Intent Tags - small, atomic conceptual units that encapsulate user intent - for exploring granular and non-linear micro-prompting interactions for Human-GenAI co-creation workflows. Our user study with 12 participants provides insights into the value of flexibly expressing intent across varying levels of ambiguity, meta-intent elicitation, and the benefits and challenges of intent tag-driven workflows. We conclude by discussing the broader implications of our findings and design considerations for GenAI-supported content creation workflows.

31 pages, 30 figures, 3 tables. To appear in the Proceedings of the 2025 ACM CHI Conference on Human Factors in Computing Systems, Yokohama, Japan

References in corpus (17)

• On the Opportunities and Risks of Foundation Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models
• Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation
• Graphologue: Exploring Large Language Model Responses with Interactive Diagrams
• Exploring Challenges and Opportunities to Support Designers in Learning to Co-create with AI-based Manufacturing Design Tools
• "What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
• DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models
• PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions
• User Intent Prediction in Information-seeking Conversations
• Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work: Beyond Mechanised Plagiarism and Stochastic Parrots
• Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models
• Interactive AI Alignment: Specification, Process, and Evaluation Alignment
• Beyond Prompts: Exploring the Design Space of Mixed-Initiative Co-Creativity Systems
• Foundation models in brief: A historical, socio-technical focus
• Imagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivation
• Knowledge-Decks: Automatically Generating Presentation Slide Decks of Visual Analytics Knowledge Discovery Applications