Symbolic AI for XAI: Evaluating LFIT Inductive Programming for Fair and Explainable Automatic Recruitment

TL;DR

This paper explores the use of LFIT, an inductive logic programming technique, to generate human-readable explanations for machine learning models in fair recruitment, aiming to improve transparency and fairness.

Contribution

It demonstrates the applicability of LFIT for creating declarative explanations in a real-world AI scenario involving fair recruitment and soft biometric data.

Findings

LFIT can learn propositional logic theories from black-box models.

The methodology supports fair recruitment by explaining ranking decisions.

Proposed scheme is adaptable to other domains.

Abstract

Machine learning methods are growing in relevance for biometrics and personal information processing in domains such as forensics, e-health, recruitment, and e-learning. In these domains, white-box (human-readable) explanations of systems built on machine learning methods can become crucial. Inductive Logic Programming (ILP) is a subfield of symbolic AI aimed to automatically learn declarative theories about the process of data. Learning from Interpretation Transition (LFIT) is an ILP technique that can learn a propositional logic theory equivalent to a given black-box system (under certain conditions). The present work takes a first step to a general methodology to incorporate accurate declarative explanations to classic machine learning by checking the viability of LFIT in a specific AI application scenario: fair recruitment based on an automatic tool generated with machine learning methods for ranking Curricula Vitae that incorporates soft biometric information (gender and ethnicity). We show the expressiveness of LFIT for this specific problem and propose a scheme that can be applicable to other domains.