Short-form generation on BioASQ
84AUROCSeSE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SeSEModel=Llama-3.1-70B2025.11 | 84 | 77 | |
| KLEModel=Llama-3.1-70B2025.11 | 83 | 77 | |
| SGDModel=Llama-3.1-70B2025.11 | 81 | 77 | |
| SEModel=Llama-3.1-70B2025.11 | 79 | 74 | |
| SeSEModel=Qwen-2-7B2025.11 | 79 | 68 | |
| SGDModel=Qwen-2-7B2025.11 | 78 | 66 | |
| KLEModel=Qwen-2-7B2025.11 | 78 | 67 | |
| ERModel=Qwen-2-72B2025.11 | 76 | 70 | |
| SeSEModel=Qwen-2-72B2025.11 | 76 | 75 | |
| SCModel=Llama-3.1-70B2025.11 | 75 | 72 | |
| P(True)Model=Qwen-2-7B2025.11 | 75 | 67 | |
| KLEModel=Qwen-2-72B2025.11 | 75 | 72 | |
| P(True)Model=Llama-3.1-70B2025.11 | 74 | 72 | |
| LN-PEModel=Llama-3.1-70B2025.11 | 74 | 72 | |
| SCModel=Qwen-2-7B2025.11 | 74 | 66 | |
| LN-PEModel=Qwen-2-7B2025.11 | 74 | 66 | |
| SCModel=Qwen-2-72B2025.11 | 74 | 71 | |
| ERModel=Llama-3.1-70B2025.11 | 73 | 74 | |
| SEModel=Qwen-2-7B2025.11 | 73 | 65 | |
| SEModel=Qwen-2-72B2025.11 | 73 | 71 | |
| SGDModel=Qwen-2-72B2025.11 | 73 | 73 | |
| ERModel=Qwen-2-7B2025.11 | 72 | 68 | |
| SeSEModel=Llama-3.1-8B2025.11 | 70 | 58 | |
| P(True)Model=Qwen-2-72B2025.11 | 70 | 70 | |
| LN-PEModel=Qwen-2-72B2025.11 | 70 | 70 | |
| P(True)Model=Llama-3.1-8B2025.11 | 68 | 56 | |
| KLEModel=Llama-3.1-8B2025.11 | 68 | 57 | |
| ERModel=Llama-3.1-8B2025.11 | 67 | 57 | |
| SCModel=Llama-3.1-8B2025.11 | 66 | 55 | |
| SGDModel=Llama-3.1-8B2025.11 | 66 | 56 | |
| LN-PEModel=Llama-3.1-8B2025.11 | 64 | 54 | |
| SEModel=Llama-3.1-8B2025.11 | 64 | 53 |