Conference Papers Year : 2023

Bias Identification in Language Models is Biased

Keywords

Fichier principal
Vignette du fichier
1WAI1_paper_8_nonanonymous.pdf (184) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04171198 , version 1 (26-07-2023)

Licence

Identifiers

  • HAL Id : hal-04171198 , version 1

Cite

Fanny Ducel, Aurélie Névéol, Karën Fort. Bias Identification in Language Models is Biased. Workshop on Algorithmic Injustice 2023, Jun 2023, Amsterdam, Netherlands. ⟨hal-04171198⟩
187 View
411 Download

Share

More