Framework makes human and AI understandings match better in tasks
Alignment Games: A Framework for Conceptual Repair in Human-AI Collaboration
Human-Computer InteractionArtificial Intelligence
Summary
People can have different ideas about what a task means, which causes confusion when working with AI. The authors introduce a method called Alignment Games that helps show and fix these differences while humans and AI collaborate. This method looks at what matters in a task, like priorities and rules, and allows changing either the situation or the way the AI thinks to reach better agreement. They demonstrate how this approach helps in creating educational materials, code, and arguments. This makes it easier for AI tools to understand what people really want.
What this means in practice
- •For content creators: Improve AI tools that generate educational or creative content by making task goals clearer and adjustable during use.
- •For software developers: Build AI-assisted design or writing tools that detect and fix misunderstandings about user goals in real-time.
Authors
Hari Subramonyam, Maneesh Agrawala, Sean Follmer
Abstract
The meaning of a concept in use is shaped by the situation, task, goals, and prior knowledge. For example, a request to make a poster "visually appealing for a five-year-old" might evoke bright colors and cartoon imagery for one collaborator, but less text, bold shapes, and visual simplicity for another. We call such task-relevant differences conceptual misalignment. We introduce Alignment Games, a framework for making these differences visible and repairable during human-AI interaction. Drawing on theories of situated conceptualization, we characterize task-specific conceptual frames in terms of relevant attributes, values, relations, constraints, and priorities. We then define alignment moves that intervene on the situation, the reasoning used to interpret it, or the resulting frame. Through examples from educational content generation, creative coding, and argumentative writing, we show how these moves can be composed into repair sequences and derive design principles for supporting task-sufficient conceptual alignment at runtime.