List your company

Persona-based Summarization on Amazon Reviews

0.722RefBS-RRL
0.713160.7154550.717750.720045Dec 12, 2025

Evaluation results

MethodLinks
RLTraining Mode=Reinforcement Learning, Optimization=PPO2025.120.7220.75160.8345
SFTTraining Mode=Supervised Fine-Tuning, Framework=Tinker Cookbook2025.120.71850.75420.8238
IPTFull Name=Instruction Prompt Tuning Model2025.120.71460.76060.8172
BaseBackbone=Qwen-4B2025.120.71350.76180.8257