Excited to share a new paper on language models and discrimination!

Our dataset covers 70 diverse decision scenarios spanning business, finance, education, and more

1/

https://t.co/W6jvXuF6fe (original) (raw)

Excited to share a new paper on language models and discrimination! Our dataset covers 70 diverse decision scenarios spanning business, finance, education, and more 1/

user avatar

Anthropic

@AnthropicAI

Dec 7, 2023

We’re releasing a new dataset for measuring discrimination across 70 different potential applications of language models, including loan applications, visa approvals, and security clearances. We’ve used this dataset to measure discrimination in LMs and develop new mitigations.

A title card for the paper. Top left: “Evaluating and Mitigating Discrimination in Language Model Decisions. Tamkin et al.” Bottom left: Anthropic logotype. Right: A monochrome image of a stone wall made up of rough, uneven rocks. The wall has fewer stones in the middle, suggesting one could almost climb over it. The wall stretches across a grassy field with hills and trees in the distance. The sky above is cloudy.

7:12 PM · Dec 7, 202326.7KViews