Summarization on CNN (ROUGE-1 F)
42.2ROUGE-1 F-ScoreCriSPO
Evaluation Results
| Method | Links | |
|---|---|---|
| CriSPOLLM=Claude3 Sonnet, Few-shot setting=0-shot2024.10 | 42.2 | |
| CriSPOLLM=Claude Instant, Few-shot setting=3-shot2024.10 | 42.1 | |
| CriSPOLLM=Claude3 Sonnet, Few-shot setting=3-shot2024.10 | 41.6 | |
| CriSPOLLM=Llama3 8B, Few-shot setting=0-shot, Optimizer=Claude-32024.10 | 41.5 | |
| ManualLLM=Claude Instant, Few-shot setting=3-shot2024.10 | 40.4 | |
| ManualLLM=Claude3 Sonnet, Few-shot setting=3-shot2024.10 | 40.3 | |
| CriSPOLLM=Claude Instant, Few-shot setting=0-shot2024.10 | 40.1 | |
| OPROLLM=Claude3 Sonnet, Few-shot setting=0-shot2024.10 | 39.7 | |
| OPROLLM=Claude Instant, Few-shot setting=0-shot2024.10 | 39.5 | |
| OPROLLM=Llama3 8B, Few-shot setting=0-shot, Optimizer=Claude-32024.10 | 39.1 | |
| ManualLLM=Claude3 Sonnet, Few-shot setting=0-shot2024.10 | 38.8 | |
| CriSPOLLM=Mistral 7B, Few-shot setting=0-shot2024.10 | 38.5 | |
| CriSPOLLM=Mistral 7B, Few-shot setting=3-shot2024.10 | 38.5 | |
| ManualLLM=Llama3 8B, Few-shot setting=0-shot2024.10 | 37.9 | |
| ManualLLM=Claude Instant, Few-shot setting=0-shot2024.10 | 37.5 | |
| OPROLLM=Mistral 7B, Few-shot setting=0-shot2024.10 | 36.5 | |
| ManualLLM=Mistral 7B, Few-shot setting=0-shot2024.10 | 30.9 | |
| ManualLLM=Mistral 7B, Few-shot setting=3-shot2024.10 | 30.7 |