List your company

LLM Alignment on HelpSteer (test)

8.34AlpacaEval 2 WRPD
0.46722.51114.5556.5989Aug 11, 2025

Evaluation results

MethodLinks
PDModel=Qwen2.5-7B, Strategy Group=SELT2025.088.3412.98——
PD (rati.)Model=Qwen2.5-7B, Strategy Group=SELT2025.087.9712.73——
DMPOModel=Qwen2.5-7B, Strategy Group=FULL2025.087.612.26——
AVG.Model=Qwen2.5-7B, Strategy Group=FULL2025.087.5912.19——
PD (ours)Model=Llama3.1-8B, Category=SELT2025.087.5512.131.198.7
RAFModel=Llama3.1-8B, Category=SELT2025.086.5810.461.16.6
PD (rati.)Model=Llama3.1-8B, Category=SELT2025.086.5712.411.135
RAFModel=Qwen2.5-7B, Strategy Group=SELT2025.086.5710.98——
RANDModel=Qwen2.5-7B, Strategy Group=SELT2025.086.3810.69——
AVG.Model=Llama3.1-8B, Category=FULL2025.086.189.551.0310
ALLModel=Qwen2.5-7B, Strategy Group=FULL2025.086.1710.63——
DMPOModel=Llama3.1-8B, Category=FULL2025.086.0110.351.0913.7
OVA.Model=Qwen2.5-7B, Strategy Group=FULL2025.085.8711.71——
OVA.Model=Llama3.1-8B, Category=FULL2025.085.759.95110
ALLModel=Llama3.1-8B, Category=FULL2025.085.559.971.0210
RANDModel=Llama3.1-8B, Category=SELT2025.085.538.50.985
SFTModel=Llama3.1-8B, Category=INIT2025.084.528.250.760
SFTModel=Qwen2.5-7B, Strategy Group=INIT2025.084.369.12——
PDModel=Qwen2.5-7B, Strategy Group=SELT2025.081.22———
PD (rati.)Model=Qwen2.5-7B, Strategy Group=SELT2025.081.21———
DMPOModel=Qwen2.5-7B, Strategy Group=FULL2025.081.08———
RAFModel=Qwen2.5-7B, Strategy Group=SELT2025.081.05———
AVG.Model=Qwen2.5-7B, Strategy Group=FULL2025.081.03———
ALLModel=Qwen2.5-7B, Strategy Group=FULL2025.081.03———
OVA.Model=Qwen2.5-7B, Strategy Group=FULL2025.081———
RANDModel=Qwen2.5-7B, Strategy Group=SELT2025.080.98———
SFTModel=Qwen2.5-7B, Strategy Group=INIT2025.080.77———