Casual Mention Span Extraction on SHINES
85F1 ScoreLlama-3.1-8B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.1-8B-InstructProtocol=Multitask Fine-tuning, CESM-100=true2025.06 | 85 | |
| Mental-Alpaca-7BProtocol=Multitask Fine-tuning, CESM-100=true2025.06 | 83 | |
| Llama-3.1-8B-InstructProtocol=Multitask Fine-tuning, CESM-100=false2025.06 | 83 | |
| Mental-Alpaca-7BProtocol=Multitask Fine-tuning, CESM-100=false2025.06 | 81 | |
| MentaLLaMA-chat-7BProtocol=Multitask Fine-tuning, CESM-100=true2025.06 | 80 | |
| MentaLLaMA-chat-7BProtocol=Multitask Fine-tuning, CESM-100=false2025.06 | 78 |