List your company
ResearchFormerly WizWand

Summarization on CNN (BERTScore F)

87.8BERTScore FCriSPO
85.51286.10686.787.294Oct 3, 2024
Updated 8mo ago

Evaluation results

MethodLinks
CriSPOLLM=Claude 3 Sonnet, Prompt Strategy=Automatic, Shots=0-shot2024.1087.8
CriSPOLLM=Claude 3 Sonnet, Prompt Strategy=Automatic, Shots=3-shot, Example Selection=true2024.1087.8
CriSPOLLM=Claude Instant, Prompt Strategy=Automatic, Shots=3-shot, Example Selection=true2024.1087.7
ManualLLM=Claude 3 Sonnet, Shots=3-shot, Example Selection=true2024.1087.7
ManualLLM=Claude Instant, Shots=3-shot, Example Selection=true2024.1087.6
CriSPOLLM=Llama3 8B, Prompt Strategy=Automatic, Shots=0-shot, Optimizer=Claude 3 Sonnet2024.1087.6
OPROLLM=Claude Instant, Prompt Strategy=Automatic2024.1087.5
OPROLLM=Claude 3 Sonnet, Prompt Strategy=Automatic2024.1087.5
ManualLLM=Claude 3 Sonnet, Shots=0-shot2024.1087.4
OPROLLM=Llama3 8B, Prompt Strategy=Automatic, Optimizer=Claude 3 Sonnet2024.1087.4
CriSPOLLM=Mistral 7B, Prompt Strategy=Automatic, Shots=0-shot2024.1087.3
CriSPOLLM=Mistral 7B, Prompt Strategy=Automatic, Shots=3-shot, Example Selection=true2024.1087.3
CriSPOLLM=Claude Instant, Prompt Strategy=Automatic, Shots=0-shot2024.1087.2
ManualLLM=Llama3 8B, Shots=0-shot2024.1087.2
ManualLLM=Claude Instant, Shots=0-shot2024.1087
OPROLLM=Mistral 7B, Prompt Strategy=Automatic2024.1087
ManualLLM=Mistral 7B, Shots=3-shot, Example Selection=true2024.1085.8
ManualLLM=Mistral 7B, Shots=0-shot2024.1085.6