Artificial Intelligence and Skills: Evidence from Contrastive Learning in Online Job Vacancies

TL;DR

This study uses contrastive learning and large language models to analyze 14 million Chinese job vacancies, revealing that AI adoption influences skill requirements by reducing information asymmetry and enabling anticipation of future skill trends.

Contribution

It introduces a novel XMLC algorithm with contrastive learning and LLM data augmentation to map job skills to the ESCO framework, demonstrating AI's impact on skill evolution.

Findings

AI adoption expands skill portfolios in firms.

AI reduces labor market information asymmetry.

AI promotes demand for future-oriented skills.

Abstract

We investigate the impact of artificial intelligence (AI) adoption on skill requirements using 14 million online job vacancies from Chinese listed firms (2018-2022). Employing a novel Extreme Multi-Label Classification (XMLC) algorithm trained via contrastive learning and LLM-driven data augmentation, we map vacancy requirements to the ESCO framework. By benchmarking occupation-skill relationships against 2018 O*NET-ESCO mappings, we document a robust causal relationship between AI adoption and the expansion of skill portfolios. Our analysis identifies two distinct mechanisms. First, AI reduces information asymmetry in the labor market, enabling firms to specify current occupation-specific requirements with greater precision. Second, AI empowers firms to anticipate evolving labor market dynamics. We find that AI adoption significantly increases the demand for "forward-looking" skills--those absent from 2018 standards but subsequently codified in 2022 updates. This suggests that AI allows firms to lead, rather than follow, the formal evolution of occupational standards. Our findings highlight AI's dual role as both a stabilizer of current recruitment information and a catalyst for proactive adaptation to future skill shifts.