Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis

Open Webpage

Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu

Published: 16 Oct 2024, Last Modified: 25 Mar 2026Proceedings of the AAAI/ACM Conference on AI Ethics and SocietyEveryoneRevisionsCC BY-SA 4.0