Discovering the rationale of decisions: towards a method for aligning learning and reasoning

Cor Steging, Silja Renooij, Bart Verheij

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent rationale. In this paper, we introduce a knowledge-driven method for model-agnostic rationale evaluation using dedicated test cases, similar to unit-testing in professional software development. We apply this new quantitative human-in-the-loop method in a machine learning experiment aimed at extracting known knowledge structures from artificial datasets from a real-life legal setting. We show that our method allows us to analyze the rationale of black box machine learning systems by assessing which rationale elements are learned or not. Furthermore, we show that the rationale can be adjusted using tailor-made training data based on the results of the rationale evaluation.

    Original languageEnglish
    Title of host publicationProceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021
    EditorsA.Z. Wyner
    PublisherAssociation for Computing Machinery
    Pages235-239
    Number of pages5
    ISBN (Electronic)9781450385268
    DOIs
    Publication statusPublished - 21 Jun 2021

    Publication series

    NameProceedings of the 18th International Conference on Artificial Intelligence and Law, ICAIL 2021

    Bibliographical note

    DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

    Keywords

    • explainable AI
    • learning knowledge from data
    • machine learning
    • responsible AI

    Fingerprint

    Dive into the research topics of 'Discovering the rationale of decisions: towards a method for aligning learning and reasoning'. Together they form a unique fingerprint.

    Cite this