跳到正文
arXiv cs.CY· Ernesto Biempica, Emiliano Bruner, Juan F Poyatos·· 23 小时前AI 评分24

人类-LLM 认知扩展(HLCE):研究耦合认知的方法论框架

Human-LLM Cognitive Extension: A Framework for Studying Coupled Cognition

AI 导读

研究者提出人类-LLM 认知扩展(HLCE)框架,主张按四种不同认知系统区分实验设计、测量与因果推断:人类独立行动、人工智能体、人-LLM 联合配置,以及分工后的人类。该框架将耦合架构本身视为实验对象,并区分性能增强、系统级互补、交互后人类变化与构成性认知整合等不同主张。作者用一个合成诊断实验展示了两种连接配置如何影响联合问题解决的组织方式,即使最终结果不变。

正文 · 原文

View PDF HTML (experimental)

Abstract:Recent research on the use of Large Language Models (LLMs) reports divergent cognitive outcomes, including improved assisted performance, limited transfer, and compromised unaided learning. Here, we argue that part of this seeming inconsistency arises because studies often assess different cognitive systems without making the unit of analysis explicit. Building on work in extended and distributed cognition, we propose the Human-LLM Cognitive Extension (HLCE) as a methodological framework for matching experimental designs, measures, and causal inferences to four distinct systems: the human acting independently, the artificial agent, the joined human-LLM configuration, and the human after division. The framework also treats the coupling architecture as part of the experimental object. HLCE separates performance augmentation, system-level complementarity, post-interaction human change, and stronger claims of constitutive cognitive integration. This separation can improve the interpretation of existing evidence and guide the design of human-LLM interactions without assuming in advance that these configurations constitute extended minds. We illustrate the application of HLCE with a synthetic diagnostic experiment comparing two connecting configurations that differ in how supporting information is communicated. The example highlights how distinct couplings can shape the organization of joint problem-solving, even when the final outcome remains unchanged. Overall, HLCE provides a methodological basis for designing controlled experiments and interpreting evidence across distinct forms of human-LLM cognitive interaction.
Comments: 24 pages, two supplementary tables
Subjects: Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
Cite as: arXiv:2611.24149 [cs.CY]
  (or arXiv:2611.24149v1 [cs.CY] for this version)
  https://doi.org/10.48550/arXiv.2611.24149

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Juan F Poyatos [view email]
[v1] Wed, 18 Nov 2026 09:54:43 UTC (80 KB)

来源:arXiv cs.CY · arxiv.org