On the Interaction of Belief Bias and Explanations

Ana Valeria González, Anna Rogers, Anders Søgaard

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


    A myriad of explainability methods have been proposed in recent years, but there is little consensus on how to evaluate them. While automatic metrics allow for quick benchmarking, it isn't clear how such metrics reflect human interaction with explanations. Human evaluation is of paramount importance, but previous protocols fail to account for belief biases affecting human performance, which may lead to misleading conclusions. We provide an overview of belief bias, its role in human evaluation, and ideas for NLP practitioners on how to account for it. For two experimental paradigms, we present a case study of gradient-based explainability introducing simple ways to account for humans' prior beliefs: models of varying quality and adversarial examples. We show that conclusions about the highest performing methods change when introducing such controls, pointing to the importance of accounting for belief bias in evaluation.
    TitelFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021
    Antal sider13
    ForlagAssociation for Computational Linguistics
    Publikationsdato1 aug. 2021
    StatusUdgivet - 1 aug. 2021


    Dyk ned i forskningsemnerne om 'On the Interaction of Belief Bias and Explanations'. Sammen danner de et unikt fingeraftryk.