arxiv:2406.11614
YihuaiHong
YihuaiHong
AI & ML interests
NLP, Interpretability, LLM
Organizations
None yet
Papers
1
models
10
YihuaiHong/llama2-7b_dpo_unlearn_on_id_27_concept
Updated
•
3
YihuaiHong/llama2-7b_grad_ascent_Needle_unlearn_on_id_27_concept
Updated
•
4
YihuaiHong/llama2-7b_grad_ascent_unlearn_on_id_27_concept
Updated
•
5
YihuaiHong/llama2-7b_grad_ascent_Needle_unlearn_on_id_26_concept
Updated
•
4
YihuaiHong/llama2-7b_grad_ascent_unlearn_on_id_26_concept
Updated
•
4
YihuaiHong/llama2-7b_dpo_unlearn_on_id_26_concept
Updated
•
3
YihuaiHong/llama2-7b_npo_KL_unlearn_on_id_27_concept
Updated
•
4
YihuaiHong/llama2-7b_npo_KL_unlearn_on_id_26_concept
Updated
•
3
YihuaiHong/llama2-7b_npo_unlearn_on_id_26_concept
Updated
•
3
YihuaiHong/llama2-7b_npo_unlearn_on_id_27_concept
Updated
•
5