biastest-animalab.github.io - BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models

home > domains > biastest-animalab.github.io

Description: Deformable Neural Radiance Fields creates free-viewpoint portraits (nerfies) from casually captured videos.

nerf (134) d-nerf (47) nerfies (46)

Example domain paragraphs

BiasTestGPT framework uses ChatGPT controllable sentence generation for creating dynamic datasets for testing social biases on open-sourced Pretrained Language Models (PLMs).

HuggingFace tool for on-the-fly social bias testing and dataset generation.

We provide a dataset of generated sentences for several well established and novel biases, including challenging intersectional biases.

Links to biastest-animalab.github.io (1)

• rkocielnik.com Rafal Kocielnik