On Explainable AI and Abductive Inference

Kyrylo Medianovskyi, Ahti Veikko Pietarinen*

*Corresponding author for this work

    Research output: Contribution to journalJournal articlepeer-review

    5 Citations (Scopus)

    Abstract

    Modern explainable AI (XAI) methods remain far from providing human-like answers to ‘why’ questions, let alone those that satisfactorily agree with human-level understanding. Instead, the results that such methods provide boil down to sets of causal attributions. Currently, the choice of accepted attributions rests largely, if not solely, on the explainee’s understanding of the quality of explanations. The paper argues that such decisions may be transferred from a human to an XAI agent, provided that its machine-learning (ML) algorithms perform genuinely abductive inferences. The paper outlines the key predicament in the current inductive paradigm of ML and the associated XAI techniques, and sketches the desiderata for a truly participatory, second-generation XAI, which is endowed with abduction.

    Original languageEnglish
    Article number35
    Number of pages15
    JournalPhilosophies
    Volume7
    Issue number2
    DOIs
    Publication statusPublished - Apr 2022

    Scopus Subject Areas

    • Philosophy
    • History and Philosophy of Science

    User-Defined Keywords

    • abduction
    • causal attributions
    • counterfactuals
    • explainable AI (XAI)
    • explanation
    • induction
    • machine learning
    • understanding

    Fingerprint

    Dive into the research topics of 'On Explainable AI and Abductive Inference'. Together they form a unique fingerprint.

    Cite this