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.
Figures & tables
Figure 1: PCA biplot of 11 AI exposure indices. All indices load positively on PC1 (general cognitive AI relevance). PC2 separates augmentation measures (negative loading: AHC, Felten) from substitution measures (positive loading: SUB scores, Eloundou α ).
Figure 2: Pairwise Pearson correlations across 11 AI exposure indices at the 6-digit SOC level ( n=207 ). AHC (Haiku) correlates most strongly with Eloundou γ ( r=0.85 ) and Felten AIOE ( r=0.79 ), confirming convergent validity.
Figure 3: Bland–Altman agreement plot for Haiku vs. Sonnet augmentation scores ( n=3,666 ). The mean bias ( + 8.6 points, red line) is constant across the score range, consistent with a systematic level shift rather than scale-dependent disagreement.
Figure 4: Three-way inter-model agreement on augmentation scores. Left: Haiku vs. Sonnet ( r=0.77 , within-family). Center: Haiku vs. GPT-4o-mini ( r=0.41 , cross-family). Right: Sonnet vs. GPT-4o-mini ( r=0.31 ). Dashed red: fitted line. Dotted gray: 45-degree identity.
Figure 5: Prompt sensitivity analysis. Left: Spearman rank correlations across four prompt variants. Right: absolute scale varies by prompt framing, but rankings are preserved.
Figure 6: Measurement error correction: OLS underestimates the AHC coefficient due to attenuation bias. ORIV (using Sonnet as instrument for Haiku) recovers a 25% larger coefficient. The external IV from Espinal Maya [2] yields the largest estimate, consistent with additional endogeneity correction.
Figure 7: Incremental R2 : AHC and Frey–Osborne capture complementary information. Together, they explain 0.86 percentage points more wage variance than controls alone.