DeepSeek uses a simple grading process based on output accuracy and formatting rules rather than complex AI-based feedback to evaluate the model's reasoning and generate reward signals for RL training
factualpending
Evidence Quote
“rather than using a complex AI to give the model fine grain feedback deep seek uses simple rules to evaluate the model's final output on accuracy and formatting”
Created: 8/11/2026, 6:44:59 AM
Your notes
Loading notes...