LADICA: A Large Shared Display Interface for Generative AI Cognitive Assistance in Co-Located Team Collaboration

2024-09-21

arXiv.org

AI Summary

Existing large shared-display interfaces for team collaboration often compromise human agency or suffer from functional limitations, hindering the harnessing of collective cognitive dynamics. This paper addresses offline co-located collaboration by proposing LADICA—a novel system grounded in a dual-track paradigm of “LLM-augmented assistance + human-in-the-loop control.” LADICA integrates real-time speech understanding (ASR + LLM), dynamic knowledge graph construction, and multi-view collective cognition visualization to support brainstorming, idea structuring, and multi-perspective analysis. It continuously extracts semantic content from discussions, maps conceptual relationships, and enhances mutual awareness and workspace synchronization among participants. Empirical evaluation demonstrates that LADICA significantly improves idea generation quality, organizational efficiency, and mutual awareness. Users consistently rate it highly for naturalness, controllability, and cognitive support effectiveness.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large shared displays, such as digital whiteboards, are useful for supporting co-located team collaborations by helping members perform cognitive tasks such as brainstorming, organizing ideas, and making comparisons. While recent advancement in Large Language Models (LLMs) has catalyzed AI support for these displays, most existing systems either only offer limited capabilities or diminish human control, neglecting the potential benefits of natural group dynamics. Our formative study identified cognitive challenges teams encounter, such as diverse ideation, knowledge sharing, mutual awareness, idea organization, and synchronization of live discussions with the external workspace. In response, we introduce LADICA, a large shared display interface that helps collaborative teams brainstorm, organize, and analyze ideas through multiple analytical lenses, while fostering mutual awareness of ideas and concepts. Furthermore, LADICA facilitates the real-time extraction of key information from verbal discussions and identifies relevant entities. A lab study confirmed LADICA's usability and usefulness.

Problem

• Enhances co-located team collaboration with AI
• Addresses cognitive challenges in group dynamics
• Facilitates real-time information extraction from discussions

Innovation

• Large shared display interface
• Real-time key information extraction
• Cognitive assistance for collaboration