List your company

Factuality Evaluation on Biography

29.4Correctness CountYi-1.5-9B
4.75211.15117.5523.949Jun 18, 2024

Evaluation results

MethodLinks
Yi-1.5-9BCategory=Open-source Models2024.0629.456.91000.34
DeepSeekV2-LiteCategory=Open-source Models2024.062832.4960.458
Ministral-8BCategory=Open-source Models2024.0622.737.31000.378
Qwen2.5-7BCategory=Open-source Models2024.0620.923.1730.467
ITIBase Model=Llama-3.1-8B-Instruct2024.0619.116.1900.512
FACTBase Model=Llama-3.1-8B-Instruct, Algorithm=DPO2024.0618.112.3850.506
Llama-3.1-8BCategory=Open-source Models2024.0617.612.5840.487
RLFHBase Model=Qwen2.5-7B-Instruct2024.0617.515.5590.523
RLFHBase Model=Llama-3.1-8B-Instruct2024.0617.311790.558
DOLABase Model=Llama-3.1-8B-Instruct2024.0615.620.4840.399
Falcon3-10BCategory=Open-source Models2024.0613.522.61000.357
FACTBase Model=Llama-3.1-8B-Instruct, Algorithm=SFT2024.065.74990.541