List your company
ResearchFormerly WizWand

Instruction Following on FollowRAG Instruction

42.3FollowRAG Instruction ScoreCaR
36.26837.83439.440.966Feb 11, 2025
Updated 8mo ago

Evaluation results

MethodLinks
CaRTraining Dataset=Alpaca, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0242.3
CaRTraining Dataset=Alpaca, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0241.4
NuggetsTraining Dataset=Alpaca, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0241.1
CaRTraining Dataset=Alpaca, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0241
NuggetsTraining Dataset=Alpaca, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0240.6
NuggetsTraining Dataset=Alpaca, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0240.6
IFDTraining Dataset=Alpaca, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0240.4
IFDTraining Dataset=Alpaca, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0240.2
NOVATraining Dataset=Alpaca, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0240.1
IFDTraining Dataset=Alpaca, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0239.6
FLAME-DPOfactTraining Dataset=Alpaca, Base Model=LLaMA-3-8B2025.0239.2
NOVATraining Dataset=Alpaca, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0239.1
NOVATraining Dataset=Alpaca-GPT4, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0239.1
NOVATraining Dataset=Alpaca, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0238.8
VanillaTraining Dataset=Alpaca, Selection Ratio=100%, Base Model=LLaMA-3-8B2025.0238.7
SELF-EVALTraining Dataset=Alpaca, Base Model=LLaMA-3-8B2025.0238.5
NuggetsTraining Dataset=Alpaca-GPT4, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0238.5
CaRTraining Dataset=Alpaca-GPT4, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0238.1
CaRTraining Dataset=Alpaca-GPT4, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0238
CaRTraining Dataset=Alpaca-GPT4, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0238
NuggetsTraining Dataset=Alpaca-GPT4, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0238
NuggetsTraining Dataset=Alpaca-GPT4, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0238
IFDTraining Dataset=Alpaca-GPT4, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0237.9
NOVATraining Dataset=Alpaca-GPT4, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0237.8
IFDTraining Dataset=Alpaca-GPT4, Selection Ratio=10%, Base Model=LLaMA-3-8B2025.0237.8
NOVATraining Dataset=Alpaca-GPT4, Selection Ratio=15%, Base Model=LLaMA-3-8B2025.0237.5
FLAME-DPOfactTraining Dataset=Alpaca-GPT4, Base Model=LLaMA-3-8B2025.0237.2
IFDTraining Dataset=Alpaca-GPT4, Selection Ratio=5%, Base Model=LLaMA-3-8B2025.0237
VanillaTraining Dataset=Alpaca-GPT4, Selection Ratio=100%, Base Model=LLaMA-3-8B2025.0236.9
SELF-EVALTraining Dataset=Alpaca-GPT4, Base Model=LLaMA-3-8B2025.0236.5