Englisch

Schramowski, Patrick ; Turan, Cigdem ; Andersen, Nico ; Rothkopf, Constantin A. (2022)
Large pre-trained language models contain human-like biases of what is right and wrong to do.
In: Nature Machine Intelligence, 4 (3)
doi: 10.1038/s42256-022-00458-8
Artikel, Bibliographie