List your company

Summarization on Preference Optimization Summarization

0.3RewardZOPrO
0.22720.24610.2650.2839Mar 5, 2025

Evaluation results

MethodLinks
ZOPrOModel=Qwen 2.5, Parameters=1.5B2025.030.3
ZOPrOModel=Gemma 2, Parameters=2.4B2025.030.23