List your company
ResearchFormerly WizWand

Instruction Following on Instruction-Following (val)

31.1ROUGE-LAMiD
23.622425.563727.50529.4463Oct 13, 2025
Updated 8mo ago

Evaluation results

MethodLinks
AMiDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1031.1
AMiDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1030.83
DistiLLM (SRKL)Distillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1030.59
ABKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1030.49
TAIDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1029.83
DistiLLM (SRKL)Distillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1029.72
DistiLLM (SKL)Distillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1029.69
DistiLLM (SKL)Distillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1029.65
ABKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1029.64
TAIDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1029.45
GKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1029.36
AMiDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1029.24
ABKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1028.61
KDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1028.52
SFTDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1028.48
SeqKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1028.41
TAIDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1028.37
SeqKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1028.24
DistiLLM (SRKL)Distillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1028.21
SFTDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1027.96
GKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1027.9
DistiLLM (SKL)Distillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1027.88
AKLDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1027.81
AKLDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1027.69
GKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1027.06
ImitKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Large (0.8B), Student Model Parameters=0.8B2025.1026.96
SeqKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1026.07
KDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1026.03
ImitKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 Medium (0.3B), Student Model Parameters=0.3B2025.1025.93
SFTDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1025.81
AKLDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1025.62
KDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1025.25
ImitKDDistillation Setup=GPT-2 XL (1.5B) → GPT-2 (0.1B), Student Model Parameters=0.1B2025.1023.91