List your company

Summarization on TL;DR (distillation set)

27.24Word CountInitial Student
25.440825.907926.37526.8421Jun 5, 2024

Evaluation results

MethodLinks
Initial StudentBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0627.2426.688.9820.6—33.42
Standard KDBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0626.529.158.5121.84—12.47
Initial StudentBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0626.3529.048.3421.66—11.51
Standard KDBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0626.3231.4510.0423.78—37.7
SeqKDBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0626.1429.238.5721.82—13.18
PLaDBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0626.0231.4610.7924.91—40.46
f-distillBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0625.9832.0910.6524.42—38.35
SFT StudentBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0625.8829.088.4421.76—11.4
MiniLLMBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0625.8629.378.6222.03—13.73
TeacherBackbone=GPT-Neo-2.7B, Model Group=GPT-Neo2024.0625.8129.648.8222.22—15.35
MiniLLMBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0625.831.3210.4824.25—38.07
SFTBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0625.7730.069.9522.97—35.13
PLaDBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0625.7729.58.6922.08—14.76
f-distillBackbone=GPT-Neo-1.3B, Model Group=GPT-Neo2024.0625.7329.348.6221.91—13.55
SeqKDBackbone=LLaMA-2-7B, Model Group=LLaMA-22024.0625.6731.6710.4224.2—37.92
TeacherBackbone=LLaMA-2-13B, Model Group=LLaMA-22024.0625.5133.1411.425.31—45.28