Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
Paper
•
2502.16825
•
Published
•
6
Xiao Yao
YaoYX
·
AI & ML interests
NLP
Recent Activity
liked
a dataset
5 days ago
agentica-org/DeepScaleR-Preview-Dataset
updated
a model
about 2 months ago
YaoYX/llama_instruct_chosen_mu_1000sigma_rejected_mu_-2sigma_400
Organizations
