Filipino language models attribute gender and sexuality bias to concrete nouns such as people and objects, diverging from the action-heavy bias drivers observed in English models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages
Filipino language models attribute gender and sexuality bias to concrete nouns such as people and objects, diverging from the action-heavy bias drivers observed in English models.