Pith. sign in

https://github.com/ conversationai/perspectiveapi/blob/ master/api_reference.md#models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CY 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Interpreting Social Respect: A Normative Lens for ML Models

cs.CY · 2019-08-01 · conditional · novelty 5.0

Applying TCAV interpretability to two toxicity models reveals that a debiased model version changes how LGBTIQ+ identity terms are associated with toxicity in internal representations.

citing papers explorer

Showing 1 of 1 citing paper.

  • Interpreting Social Respect: A Normative Lens for ML Models cs.CY · 2019-08-01 · conditional · none · ref 1

    Applying TCAV interpretability to two toxicity models reveals that a debiased model version changes how LGBTIQ+ identity terms are associated with toxicity in internal representations.