Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
Paper
• 2502.06876 • Published
Model Merging
-
-
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
Paper • 2410.13910 • Published -
yangjinluan/3H_Merging_Llama3_Harmlessness
Updated • 2 -
yangjinluan/3H_Merging_Mistral_Helpfulness_Harmlessness
7B • Updated • 2 -
yangjinluan/3H_Merging_Llama3_Helpfulness_Honesty
Updated • 3 -
yangjinluan/3H_Merging_Mistral_Harmlessness
7B • Updated • 2 -
yangjinluan/3H_Merging_Mistral_Helpfulness_Honesty
7B • Updated • 4 -
yangjinluan/3H_Merging_Mistral_Helpfulness
7B • Updated • 1 -
yangjinluan/3H_Merging_Mistral_Honesty
7B • Updated • 9 -
yangjinluan/3H_Merging_Llama3_Helpfulness
Updated • 4 -
yangjinluan/3H_Merging_Llama3_Helpfulness_Harmlessness
Updated • 1 -
yangjinluan/3H_Merging_Llama3_Honesty
Updated