13
BiasDetection
🐠
Analyze bias and toxicity in language models
Resources: Bias, Stereotypes, and Representational Harms
Linking collected resources for this category that have a dataset, model, or demo on Hugging Face or a paper on ArXiv (inked through Hugging Face)
Note Demo
16StableBias
📖Note Demo
McGill-NLP/stereoset
Viewer • Updated • 4.23k • 1.19k • 16Note Dataset
nyu-mll/crows_pairs
Updated • 796 • 7Note Dataset
BigScienceBiasEval/crows_pairs_multilingual
Updated • 1.28k • 3Note Dataset
MilaNLProc/honest
Viewer • Updated • 5.63k • 282 • 5Note Dataset
orhunc/Bias-Evaluation-Turkish
Viewer • Updated • 38 • 200Note Dataset
-
StereoSet: Measuring stereotypical bias in pretrained language models
Paper • 2004.09456 • Published -
CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Paper • 2010.00133 • Published -
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Paper • 2010.15052 • Published -
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
Paper • 1811.08489 • Published -
Measuring Social Biases in Grounded Vision and Language Embeddings
Paper • 2002.08911 • Published -
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Models
Paper • 2202.04053 • Published -
Bias in Multimodal AI: Testbed for Fair Automatic Recruitment
Paper • 2004.07173 • Published -
Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications
Paper • 2108.02818 • Published -
Semantics derived automatically from language corpora contain human-like biases
Paper • 1608.07187 • Published -
On Measuring Social Biases in Sentence Encoders
Paper • 1903.10561 • Published -
Assessing Social and Intersectional Biases in Contextualized Word Representations
Paper • 1911.01485 • Published -
Stable Bias: Analyzing Societal Representations in Diffusion Models
Paper • 2303.11408 • Published -
allenai/persona-bias
Updated • 42 • 11