List your company

Helpfulness Evaluation on Helpfulness

97Average Win RateCurriculum-RLAIF
84.5287.769194.24May 26, 2025

Evaluation results

MethodLinks
Curriculum-RLAIFBase Model=Qwen2.5-32B, Category=Curriculum2025.0597
Curriculum-RLAIFBase Model=LLaMA-3-8B, Category=Curriculum2025.0595
Internal Eval.Base Model=Qwen2.5-32B, Category=Curriculum2025.0594
Curriculum-RLAIFBase Model=Gemma-1-2B, Category=Curriculum2025.0593
Conventional RLAIFBase Model=Qwen2.5-32B, Category=Non-Curriculum2025.0593
Implicit Eval. (DPO)Base Model=Qwen2.5-32B, Category=Curriculum2025.0593
RLCDBase Model=Qwen2.5-32B, Category=Non-Curriculum2025.0592
Internal Eval.Base Model=LLaMA-3-8B, Category=Curriculum2025.0591
External Eval.Base Model=Qwen2.5-32B, Category=Curriculum2025.0591
Conventional RLAIFBase Model=LLaMA-3-8B, Category=Non-Curriculum2025.0590
Implicit Eval. (DPO)Base Model=LLaMA-3-8B, Category=Curriculum2025.0590
CAIBase Model=Qwen2.5-32B, Category=Non-Curriculum2025.0589
Internal Eval.Base Model=Gemma-1-2B, Category=Curriculum2025.0588
RLCDBase Model=LLaMA-3-8B, Category=Non-Curriculum2025.0588
RLCDBase Model=Gemma-1-2B, Category=Non-Curriculum2025.0587
External Eval.Base Model=Gemma-1-2B, Category=Curriculum2025.0587
CAIBase Model=LLaMA-3-8B, Category=Non-Curriculum2025.0587
External Eval.Base Model=LLaMA-3-8B, Category=Curriculum2025.0587
Conventional RLAIFBase Model=Gemma-1-2B, Category=Non-Curriculum2025.0586
CAIBase Model=Gemma-1-2B, Category=Non-Curriculum2025.0585
Implicit Eval. (DPO)Base Model=Gemma-1-2B, Category=Curriculum2025.0585