AIbase

Mitigating-Reasoning-LLM-Social-Bias

Public

A novel approach to mitigating social bias in Large Language Models through a multi-judge pipeline that assesses and filters reasoning steps of DeepSeek-R1.

Creat2025-05-08T17:13:09
Update2025-07-03T22:17:45
0
Stars
0
Stars Increase

Related projects