Fairness

Open Diké Leaderboard

Open Diké is an evaluation framework and leaderboard for studying the effects of model compression on bias, fairness, ethics, and safety-related metrics.

Towards an Unbiased Compression of Large Language Models

Contributions to Fairness-aware and Aligned Large Language Models

Fair-GPTQ: Bias-Aware Quantization for Large Language Models

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

Fair Text Classification via Transferable Representations

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

Fair Text Classification with Wasserstein Independence

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

An Investigation of Structures Responsible for Gender Bias in BERT and DistilBERT

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.