0

Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning

Textual entailment models reduce bias in sentence representation models by explicitly learning language logic, improving social community recognition without de-biasing.

Year
2023
Venue
arXiv 2023
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2303.05670ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of stereotypes concerning different communities that are present in popular sentence representation models, including pretrained next sentence prediction and contrastive sentence representation models. We compare such models to textual entailment models that learn language logic for a variety of downstream language understanding tasks. By comparing strong pretrained models based on text similarity with textual entailment learning, we conclude that the explicit logic learning with textual entailment can significantly reduce bias and improve the recognition of social communities, without an explicit de-biasing process

Authors

2