AI Dynamics

Global AI News Aggregator

About

Political Biases in LLMs Reinforce Media Polarization

2/ Political Biases Found in NLP Models – measures media biases in LLMs, including the fairness of downstream NLP models tuned on top of politically biased LLMs; reveals that LLMs have political leanings which reinforce existing polarization in corpora.

→ View original post on X — @dair_ai