pith. sign in

counterfactual augmentations

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

1 Pith paper citing it

fields

cs.CY 1

years

2020 1

verdicts

CONDITIONAL 1

representative citing papers

Aligning AI With Shared Human Values

cs.CY · 2020-08-05 · conditional · novelty 6.0

Introduces ETHICS benchmark showing current language models have promising but incomplete ability to predict basic human ethical judgments on text scenarios.

citing papers explorer

Showing 1 of 1 citing paper.

  • Aligning AI With Shared Human Values cs.CY · 2020-08-05 · conditional · none · ref 27

    Introduces ETHICS benchmark showing current language models have promising but incomplete ability to predict basic human ethical judgments on text scenarios.