List your company

Factuality Hallucination Evaluation on BioGEN (test)

50.5FactScoreNOVA
41.55643.87846.248.522Feb 11, 2025

Evaluation results

MethodLinks
NOVAInstruction Dataset=Alpaca - GPT4, Sample Ratio=5%2025.0250.5
NOVAInstruction Dataset=Alpaca, Sample Ratio=5%2025.0250.3
SELF-EVALInstruction Dataset=Alpaca, Sample Ratio=100%2025.0248.3
NuggetsInstruction Dataset=Alpaca, Sample Ratio=5%2025.0248.2
IFDInstruction Dataset=Alpaca, Sample Ratio=5%2025.0248.1
NOVAInstruction Dataset=Alpaca - GPT4, Sample Ratio=10%2025.0248.1
CaRInstruction Dataset=Alpaca, Sample Ratio=5%2025.0247.9
FLAME-DPO factInstruction Dataset=Alpaca, Sample Ratio=100%2025.0247.2
SELF-EVALInstruction Dataset=Alpaca - GPT4, Sample Ratio=100%2025.0247.2
NuggetsInstruction Dataset=Alpaca - GPT4, Sample Ratio=5%2025.0247.2
CaRInstruction Dataset=Alpaca - GPT4, Sample Ratio=5%2025.0246.9
NOVAInstruction Dataset=Alpaca - GPT4, Sample Ratio=15%2025.0246.9
NOVAInstruction Dataset=Alpaca, Sample Ratio=10%2025.0246.8
NuggetsInstruction Dataset=Alpaca - GPT4, Sample Ratio=10%2025.0246.8
IFDInstruction Dataset=Alpaca - GPT4, Sample Ratio=5%2025.0246.7
FLAME-DPO factInstruction Dataset=Alpaca - GPT4, Sample Ratio=100%2025.0246.3
NOVAInstruction Dataset=Alpaca, Sample Ratio=15%2025.0245.9
CaRInstruction Dataset=Alpaca - GPT4, Sample Ratio=10%2025.0245.9
NuggetsInstruction Dataset=Alpaca, Sample Ratio=10%2025.0245.8
CaRInstruction Dataset=Alpaca, Sample Ratio=10%2025.0245.2
NuggetsInstruction Dataset=Alpaca - GPT4, Sample Ratio=15%2025.0244.8
CaRInstruction Dataset=Alpaca - GPT4, Sample Ratio=15%2025.0244.6
NuggetsInstruction Dataset=Alpaca, Sample Ratio=15%2025.0244.3
CaRInstruction Dataset=Alpaca, Sample Ratio=15%2025.0243.9
IFDInstruction Dataset=Alpaca - GPT4, Sample Ratio=10%2025.0243.6
IFDInstruction Dataset=Alpaca, Sample Ratio=10%2025.0243.2
IFDInstruction Dataset=Alpaca - GPT4, Sample Ratio=15%2025.0242.9
VanillaInstruction Dataset=Alpaca, Sample Ratio=100%2025.0242.4
IFDInstruction Dataset=Alpaca, Sample Ratio=15%2025.0242.2
VanillaInstruction Dataset=Alpaca - GPT4, Sample Ratio=100%2025.0241.9