TPT

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Aug 5 18:28
Editor
Edited
Edited
2025 Aug 5 18:29
Refs
Refs

Iteration Pipeline utilizing CoT + Answer Pruning + Iterative SFT

Performance improvements are shown below:
GSM8K
  • Gemma2-2B: 41.9 → 57.6 (+15.7%p)
  • Gemma2-9B: 66.4 → 82.4 (+16.0%p)
  • LLaMA-70B: 78.6 → 91.5 (+12.9%p)
 
 
 
 
 
 
 
 
 

Recommendations