Fact-checking on HealthVer
68F1-macroiPOE-llm
Evaluation Results
| Method | Links | |
|---|---|---|
| iPOE-llmModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 68 | |
| iPOE-lb-llmModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 67 | |
| iPOE-llmModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 64 | |
| iPOE-hModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 64 | |
| iPOE-lb-hModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 64 | |
| iPOE-lb-hModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 63 | |
| iPOE-llmModel=LLama3-8B, Protocol=Zero-shot2026.05 | 63 | |
| iPOE-lb-llmModel=LLama3-8B, Protocol=Zero-shot2026.05 | 63 | |
| VanillaModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 63 | |
| iPOE-hModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 62 | |
| iPOE-lb-llmModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 62 | |
| iPOE-hModel=LLama3-8B, Protocol=Zero-shot2026.05 | 60 | |
| iPOE-lb-hModel=LLama3-8B, Protocol=Zero-shot2026.05 | 60 | |
| Rand-hModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 59 | |
| Rand-llmModel=Qwen3-30B, Protocol=Zero-shot2026.05 | 59 | |
| VanillaModel=LLama3-8B, Protocol=Zero-shot2026.05 | 41 | |
| VanillaModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 40 | |
| Rand-hModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 35 | |
| Rand-hModel=LLama3-8B, Protocol=Zero-shot2026.05 | 34 | |
| Rand-llmModel=LLama3-8B, Protocol=Zero-shot2026.05 | 34 | |
| Rand-llmModel=Qwen3-4B, Protocol=Zero-shot2026.05 | 25 |