Being Right for Whose Right Reasons?

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


  • Fulltext

    Final published version, 1.07 MB, PDF document

Explainability methods are used to benchmark the extent to which model predictions align with human rationales i.e., are ‘right for the right reasons’. Previous work has failed to acknowledge, however, that what counts as a rationale is sometimes subjective. This paper presents what we think is a first of its kind, a collection of human rationale annotations augmented with the annotators demographic information. We cover three datasets spanning sentiment analysis and common-sense reasoning, and six demographic groups (balanced across age and ethnicity). Such data enables us to ask both what demographics our predictions align with and whose reasoning patterns our models’ rationales align with. We find systematic inter-group annotator disagreement and show how 16 Transformer-based models align better with rationales provided by certain demographic groups: We find that models are biased towards aligning best with older and/or white annotators. We zoom in on the effects of model size and model distillation, finding –contrary to our expectations– negative correlations between model size and rationale agreement as well as no evidence that either model size or model distillation improves fairness.
Original languageEnglish
Title of host publicationProceedings of the 61st Annual Meeting of the Association for Computational Linguistics : Long Papers
PublisherAssociation for Computational Linguistics (ACL)
Publication date2023
ISBN (Electronic)978-1-959429-72-2
Publication statusPublished - 2023
Event61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
Duration: 9 Jul 202314 Jul 2023


Conference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
SponsorBloomberg Engineering, et al., Google Research, Liveperson, Meta, Microsoft

ID: 381636287