Phase 2
- Extract the last layer to get the importance of each word in the embedding
- Normalize the importance and use it as weight to bias
GenderBiasGPT for Regional Languages
We built a gender bias detection model in Vietnamese and Hindi to 1) Improve the social gender bias when training the LLM for these languages 2) Improve language diversity in NLP research
Log in or sign up for Devpost to join the conversation.