Being Right for Whose Right Reasons?
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Being Right for Whose Right Reasons? / Thorn Jakobsen, Terne Sasha; Cabello, Laura; Søgaard, Anders.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics : Long Papers. Vol. 1 Association for Computational Linguistics (ACL), 2023. p. 1033-1054.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Being Right for Whose Right Reasons?
AU - Thorn Jakobsen, Terne Sasha
AU - Cabello, Laura
AU - Søgaard, Anders
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
U2 - 10.18653/v1/2023.acl-long.59
DO - 10.18653/v1/2023.acl-long.59
M3 - Article in proceedings
VL - 1
SP - 1033
EP - 1054
BT - Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Y2 - 9 July 2023 through 14 July 2023
ER -
ID: 381636287