Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Caglidil, Orhun"'
Language models are trained mostly on Web data, which often contains social stereotypes and biases that the models can inherit. This has potentially negative consequences, as models can amplify these biases in downstream tasks or applications. Howeve
Externí odkaz:
http://arxiv.org/abs/2404.11726
