An MoE alignment pipeline combining two SPE-DPO-trained experts and a learned routing network reports better safety and helpfulness scores than existing dual-preference alignment baselines.
down_proj
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework
An MoE alignment pipeline combining two SPE-DPO-trained experts and a learned routing network reports better safety and helpfulness scores than existing dual-preference alignment baselines.