paper-with-me

Papers

What Type of Explanation Do Rejected Job Applicants Want? Implications for Explainable AI

2022-05-18 · Matthew Olckers, Alicia Vidler, Toby Walsh

Rejected job applicants seldom receive explanations from employers. Techniques from Explainable AI (XAI) could provide explanations at scale. Although XAI researchers have developed many different types of explanations, we know little about the type of explanations job applicants want. We use a survey of recent job applicants to fill this gap. Our survey generates three main insights. First, the current norm of, at most, generic feedback frustrates applicants. Second, applicants feel the employer has an obligation to provide an explanation. Third, job applicants want to know why they were unsuccessful and how to improve.

📄 PDF Abstract BibTeX arXiv:2205.09649

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable Artificial Intelligence (XAI)Survey

Similar Papers 제목 키워드 기반

Performative Validity of Recourse Explanations

2025-06-18 · Gunnar König, Hidde Fokkema, Timo Freiesleben, Celestine Mendler-Dünner 외

When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomeno…

counterfactualvalid

Why Finnish polytechnics reject top applicants

2019-08-15

I use a panel of higher education clearinghouse data to study the centralized assignment of applicants to Finnish polytechnics. I show that on a yearly basis, large numbers of top applicants unnecessarily remain unassign…

Incentives to Offer Algorithmic Recourse

2023-01-27 · Matthew Olckers, Toby Walsh

Due to the importance of artificial intelligence (AI) in a variety of high-stakes decisions, such as loan approval, job hiring, and criminal bail, researchers in Explainable AI (XAI) have developed algorithms to provide …

Explainable Artificial Intelligence (XAI)

Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP

2022-09-15 · Benjamin Ledel, Steffen Herbold

Context: The identification of bugs within the reported issues in an issue tracker is crucial for the triage of issues. Machine learning models have shown promising results regarding the performance of automated issue ty…

PredictionType prediction

From Facts to Foils: Designing and Evaluating Counterfactual Explanations for Smart Environments

2025-10-03 · Anna Trapp, Mersedeh Sadeghi, Andreas Vogelsang arxiv

Explainability is increasingly seen as an essential feature of rule-based smart environments. While counterfactual explanations, which describe what could have been done differently to achieve a desired outcome, are a po…