List your company

Fact-checking on HealthVer

68F1-macroiPOE-llm
23.2834.8946.558.11May 18, 2026

Evaluation results

MethodLinks
iPOE-llmModel=Qwen3-30B, Protocol=Zero-shot2026.0568
iPOE-lb-llmModel=Qwen3-30B, Protocol=Zero-shot2026.0567
iPOE-llmModel=Qwen3-4B, Protocol=Zero-shot2026.0564
iPOE-hModel=Qwen3-30B, Protocol=Zero-shot2026.0564
iPOE-lb-hModel=Qwen3-30B, Protocol=Zero-shot2026.0564
iPOE-lb-hModel=Qwen3-4B, Protocol=Zero-shot2026.0563
iPOE-llmModel=LLama3-8B, Protocol=Zero-shot2026.0563
iPOE-lb-llmModel=LLama3-8B, Protocol=Zero-shot2026.0563
VanillaModel=Qwen3-30B, Protocol=Zero-shot2026.0563
iPOE-hModel=Qwen3-4B, Protocol=Zero-shot2026.0562
iPOE-lb-llmModel=Qwen3-4B, Protocol=Zero-shot2026.0562
iPOE-hModel=LLama3-8B, Protocol=Zero-shot2026.0560
iPOE-lb-hModel=LLama3-8B, Protocol=Zero-shot2026.0560
Rand-hModel=Qwen3-30B, Protocol=Zero-shot2026.0559
Rand-llmModel=Qwen3-30B, Protocol=Zero-shot2026.0559
VanillaModel=LLama3-8B, Protocol=Zero-shot2026.0541
VanillaModel=Qwen3-4B, Protocol=Zero-shot2026.0540
Rand-hModel=Qwen3-4B, Protocol=Zero-shot2026.0535
Rand-hModel=LLama3-8B, Protocol=Zero-shot2026.0534
Rand-llmModel=LLama3-8B, Protocol=Zero-shot2026.0534
Rand-llmModel=Qwen3-4B, Protocol=Zero-shot2026.0525