Search Results for author: Jon Roozenbeek

Found 1 papers, 0 papers with code

Generative Language Models Exhibit Social Identity Biases

no code implementations24 Oct 2023 Tiancheng Hu, Yara Kyrychenko, Steve Rathje, Nigel Collier, Sander van der Linden, Jon Roozenbeek

In this study, we investigate whether ingroup solidarity and outgroup hostility, fundamental social biases known from social science, are present in 51 large language models.

Cannot find the paper you are looking for? You can Submit a new open access paper.