Bias mitigation reduces gender-occupation disparities in the embedding spaces of both encoder-only and decoder-only foundation models, producing more neutral internal representations.
In: Findings of the Association for Computational Linguistics (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Representation-Level Assessment of Bias Mitigation in Foundation Models
Bias mitigation reduces gender-occupation disparities in the embedding spaces of both encoder-only and decoder-only foundation models, producing more neutral internal representations.