Preprint
Aug 2026
A Heuristic Perspective on Debiasing Language Models
HEIMAT, a HEurIstic-style autoMATic debiasing framework for LMs, effectively mitigates bias in different cultures while maintaining the model's natural language understanding (NLU) performance.
Tian Lan, Yemin Wang, Chuancheng Shi et al.
· 0 citations