Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making

2026-02-12

AI Summary

In high-stakes human–LLM collaborative decision-making, the lack of a systematic understanding of role allocation limits both the safety and efficacy of large language model (LLM) deployment. This study introduces, for the first time, the concept of “human–LLM archetypes,” deriving 17 distinct collaboration role patterns through a scoping literature review and thematic analysis. These archetypes were empirically evaluated in a clinical diagnostic task, revealing that different role configurations significantly influence LLM output quality and decision outcomes. The findings uncover critical design trade-offs along dimensions such as control allocation, social hierarchy, cognitive intervention, and information requirements, thereby offering a theoretical framework and practical guidance for designing human–LLM collaborative systems in high-risk settings.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

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

Abstract

LLMs are increasingly supporting decision-making across high-stakes domains, requiring critical reflection on the socio-technical factors that shape how humans and LLMs are assigned roles and interact during human-in-the-loop decision-making. This paper introduces the concept of human-LLM archetypes -- defined as re-curring socio-technical interaction patterns that structure the roles of humans and LLMs in collaborative decision-making. We describe 17 human-LLM archetypes derived from a scoping literature review and thematic analysis of 113 LLM-supported decision-making papers. Then, we evaluate these diverse archetypes across real-world clinical diagnostic cases to examine the potential effects of adopting distinct human-LLM archetypes on LLM outputs and decision outcomes. Finally, we present relevant tradeoffs and design choices across human-LLM archetypes, including decision control, social hierarchies, cognitive forcing strategies, and information requirements. Through our analysis, we show that selection of human-LLM interaction archetype can influence LLM outputs and decisions, bringing important risks and considerations for the designers of human-AI decision-making systems

Problem

• human-AI collaboration
• role assignment
• LLM decision-making
• socio-technical interaction
• human-in-the-loop

Innovation

• human-LLM archetypes
• socio-technical interaction
• collaborative decision-making
• role assignment
• cognitive forcing