From Skill Extraction to Multistakeholder Recommendation: A Two-Stage Framework for Bias Governance in Skills-Based Job Matching

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.

Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems

LLM agents are increasingly used for personalization due to their ability to communicate directly with users in natural language, integrate external knowledge bases, and negotiate with other (possibly human) agents. Especially in multistakeholder AI systems with multiple distinct objectives, LLM agents are used to independently optimize for each stakeholder's goals. Here, stakeholder alignment is essential to identify and map these goals to provide LLM agents with quantifiable objectives. Plus, the way in which the outputs of the LLM agents are aggregated is fundamental to ensuring fair outcomes for all agents and, therefore, stakeholders. In this work, we identify open research challenges and propose a conceptual framework for designing fair multi-agent multistakeholder personalization systems that balance competing stakeholder objectives. Our framework integrates (i) methods to align stakeholder objectives and LLM agents, (ii) aggregation strategies, e.g., based on social choice theory, to form fair collective decisions, and (iii) stakeholder-centric evaluation procedures for both individual and collective agent behavior. We showcase our framework through a tourism use case and discuss possible applications in other domains, such as education and healthcare. Finally, we discuss domain-specific fairness tensions and review datasets for evaluating multistakeholder fairness and multi-agent personalization systems.