What's So Human about Human-AI Collaboration, Anyway? Generative AI and Human-Computer Interaction

2025-03-07

AI Summary

This study addresses the limited naturalness and efficacy of human-AI collaboration by systematically adapting established social science theories of human teamwork—such as shared intentionality, role differentiation, and situational awareness—to generative AI interaction design, thereby proposing a novel “human-like collaboration” paradigm. Through in-depth developer interviews and participatory design with end users, we developed a multimodal AI task assistant prototype. Integrating qualitative analysis, multimodal interaction modeling, and LLM-driven task support techniques, we derived a set of actionable collaborative design principles. Empirical evaluation demonstrates that our framework significantly improves user trust, human-AI intent alignment accuracy, and task completion efficiency. The work contributes both theoretical foundations and practical guidelines for advancing collaborative interaction design in generative AI systems.

Technology Category

Humans and AI: Human-AI Collaboration / Human-AI TeamingCognitive Modeling & Cognitive Systems: Social Cognition And InteractionIntelligent Robots: Human-Robot Interaction

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAISocial Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

While human-AI collaboration has been a longstanding goal and topic of study for computational research, the emergence of increasingly naturalistic generative AI language models has greatly inflected the trajectory of such research. In this paper we identify how, given the language capabilities of generative AI, common features of human-human collaboration derived from the social sciences can be applied to the study of human-computer interaction. We provide insights drawn from interviews with industry personnel working on building human-AI collaboration systems, as well as our collaborations with end-users to build a multimodal AI assistant for task support.

Problem

• Explores human-AI collaboration using generative AI models.
• Applies human-human collaboration principles to human-computer interaction.
• Develops a multimodal AI assistant for task support.

Innovation

• Generative AI enhances human-computer interaction.
• Social science principles guide AI collaboration design.
• Multimodal AI assistant developed for task support.