Equitable Evaluation via Elicitation
This addresses fairness issues in job-seeking and professional matching for individuals with different self-presentation styles, representing a novel method for a known bottleneck.
The paper tackles the problem of biased skill evaluation due to varying self-presentation styles by developing an interactive AI for skill elicitation that accurately determines skills while allowing individuals to speak in their own voice, achieving a mathematically rigorous notion of equitability with small covariance between self-presentation manner and skill evaluation error.
Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of equally qualified job-seekers with different self-presentation styles is therefore problematic. We build an interactive AI for skill elicitation that provides accurate determination of skills while simultaneously allowing individuals to speak in their own voice. Such a system can be deployed, for example, when a new user joins a professional networking platform, or when matching employees to needs during a company reorganization. To obtain sufficient training data, we train an LLM to act as synthetic humans. Elicitation mitigates endogenous bias arising from individuals' own self-reports. To address systematic model bias we enforce a mathematically rigorous notion of equitability ensuring that the covariance between self-presentation manner and skill evaluation error is small.