Sparse Interventions in Language Models with Differentiable Masking

no code implementations • 13 Dec 2021 • Nicola De Cao, Leon Schmid, Dieuwke Hupkes, Ivan Titov

Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information, and ii) do not discover small subsets of neurons responsible for a considered phenomenon.

Bias Detection Gender Bias Detection