梳理17种人与大模型协作决策模式，揭示角色分配如何影响结果
Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making
- 基于113篇论文提炼出17种人-大模型互动范式
- 实证发现不同角色分配会改变大模型输出与决策结果
- 适合关注人机协同设计的系统工程师和医疗AI研究者
大语言模型在高风险领域中日益参与决策，亟需反思其与人类在人机协同决策中角色分配的社会技术因素。本文提出「人-大模型原型」概念，即反复出现的社会技术交互模式，用以定义人与大模型在协作决策中的角色结构。通过范围文献综述与113篇支持决策的大模型论文的主题分析，我们归纳出17种人-大模型原型。随后，我们在真实临床诊断案例中评估这些原型对大模型输出与决策结果的影响。最后，我们总结了不同原型在决策控制、社会层级、认知强制策略及信息需求等方面的权衡与设计选择。研究表明，人-大模型交互原型的选择会影响大模型输出与最终决策，为人类-AI决策系统的设计者带来重要风险与考量。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。