From Skill Extraction to Multistakeholder Recommendation: A Two-Stage Framework for Bias Governance in Skills-Based Job Matching
Information Retrieval
Summary
The authors propose a two-step system to reduce bias in AI tools that match people with jobs based on skills. First, they focus on how skills are gathered and organized from candidates, especially using chatbots, and identify potential bias risks. Second, they use a multi-sided recommendation process where candidates, companies, and regulators each rank job matches, combining these rankings fairly. Their approach includes checking for biases and fairness during both steps, with some issues needing immediate fixes while others are monitored over time. This helps create more transparent and fair job matching recommendations.
Authors
Andrea Forster, Gregor Autischer, Dominik Kowald, Simone Kopeinik
Abstract
AI-based labor-market systems or platforms can affect access to job opportunities prior to organizational candidate rankings or hiring decisions. Such applications warrant caution, as biases in skill extraction, profile formation, and candidate-job matching may contribute to unfair treatment of candidates. In this paper, we propose a two-stage framework for detecting and governing bias in skills-based job matching. Stage 1, skill extraction and profile formation, addresses how candidates provide skills and preferences to the system, how the system extracts and structures this information, and the bias risks this entails, with a focus on chatbot-based elicitation. Stage 2, multistakeholder candidate-job recommendation, would embed this information in a recommender system in which candidate, company, and regulatory objectives are represented by separate agents, each producing an independent candidate-job ranking; these rankings would be combined through social choice-based aggregation into a single, auditable recommendation. The two stages are connected by a shared distinction between hard constraints, which require correction before processing continues, and soft constraints, which are logged to inform later decisions. Following an AI Act-aligned assessment methodology (based on the Fraunhofer AI Assessment Catalog), we propose using distributional auditing and counterfactual testing to produce a Stage 1 bias inventory sorted into hard and soft constraints, with the latter informing fairness thresholds for Stage 2. The same logic would apply to Stage 2: fairness metrics crossing predefined thresholds would trigger an adapted recommendation process, while smaller deviations would be logged as bias reports and persistent fairness states.