A framework estimates grammatical gender directions in contextual embeddings via controlled and natural contexts, finding unweighted controlled contexts and centroid estimators yield the purest directions.
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
citing papers explorer
-
Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts
A framework estimates grammatical gender directions in contextual embeddings via controlled and natural contexts, finding unweighted controlled contexts and centroid estimators yield the purest directions.
-
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.