Modeling Fairness in Recruitment AI via Information Flow

TL;DR

This paper presents an information flow modeling framework applied to a recruitment process to analyze how biases can emerge and propagate, enhancing transparency and fairness understanding in socio-technical AI systems.

Contribution

It introduces a novel information flow-based approach to model and analyze fairness in complex recruitment pipelines involving both AI and human decision-making.

Findings

Identified points where biases can emerge in the recruitment process

Demonstrated how biases propagate through system components

Provided insights into fairness risks and transparency improvements

Abstract

Avoiding bias and understanding the real-world consequences of AI-supported decision-making are critical to address fairness and assign accountability. Existing approaches often focus either on technical aspects, such as datasets and models, or on high-level socio-ethical considerations - rarely capturing how these elements interact in practice. In this paper, we apply an information flow-based modeling framework to a real-world recruitment process that integrates automated candidate matching with human decision-making. Through semi-structured stakeholder interviews and iterative modeling, we construct a multi-level representation of the recruitment pipeline, capturing how information is transformed, filtered, and interpreted across both algorithmic and human components. We identify where biases may emerge, how they can propagate through the system, and what downstream impacts they may have on candidates. This case study illustrates how information flow modeling can support structured analysis of fairness risks, providing transparency across complex socio-technical systems.