无法测量之物的测量：LLMs作为劳动经济学中潜在认知变量的测量工具
Measuring What Cannot Be Surveyed: LLMs as Instruments for Latent Cognitive Variables in Labor Economics
AI总结：
本文提出利用LLMs测量劳动经济学中无法通过现有调查工具精确描述的职业任务认知内容，通过四个条件验证LLMs生成分数的有效性，并应用于Augmented Human Capital Index，展示其高收敛效度和判别效度。
摘要：
本文建立了利用大型语言模型（LLMs）作为潜在经济变量测量工具的理论和实践基础，特别是用于描述职业任务认知内容的变量，这些变量的粒度无法通过现有调查工具实现。我正式提出了四个条件，以确保LLMs生成的分数构成有效的工具：语义外生性、构念相关性、单调性和模型不变性。然后，我将此框架应用于由18,796个O*NET任务陈述评分的增强人力资本指数（AHC_o），并验证其与六个现有AI暴露指数的一致性。该指数显示出强收敛效度（与Eloundou GPT-gamma相关性r=0.85，与Felten AIOE相关性r=0.79）和判别效度。主成分分析确认，与AI相关的职业测量跨越两个不同的维度——增强和替代。两个LLM模型之间的重合可靠性（n=3,666对评分）产生皮尔逊相关性r=0.76和Krippendorff's alpha=0.71。四种替代框架的提示敏感性分析显示，任务层面的排名是稳健的。显然相关的工具变量（ORIV）估计恢复出比OLS大25%的系数，与经典测量误差衰减一致。该方法学不仅适用于劳动经济学，还适用于任何需要在大规模上量化语义内容的领域。
英文摘要：
This paper establishes the theoretical and practical foundations for using Large Language Models (LLMs) as measurement instruments for latent economic variables -- specifically variables that describe the cognitive content of occupational tasks at a level of granularity not achievable with existing survey instruments. I formalize four conditions under which LLM-generated scores constitute valid instruments: semantic exogeneity, construct relevance, monotonicity, and model invariance. I then apply this framework to the Augmented Human Capital Index (AHC_o), constructed from 18,796 O*NET task statements scored by Claude Haiku 4.5, and validated against six existing AI exposure indices. The index shows strong convergent validity (r = 0.85 with Eloundou GPT-gamma, r = 0.79 with Felten AIOE) and discriminant validity. Principal component analysis confirms that AI-related occupational measures span two distinct dimensions -- augmentation and substitution. Inter-rater reliability across two LLM models (n = 3,666 paired scores) yields Pearson r = 0.76 and Krippendorff's alpha = 0.71. Prompt sensitivity analysis across four alternative framings shows that task-level rankings are robust. Obviously Related Instrumental Variables (ORIV) estimation recovers coefficients 25% larger than OLS, consistent with classical measurement error attenuation. The methodology generalizes beyond labor economics to any domain where semantic content must be quantified at scale.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
