List your company

Commonsense Question Answering on CosmosQA (test)

92.25EMMetaTuner-J
22.3140.467558.62576.7825Sep 29, 2025

Evaluation results

MethodLinks
MetaTuner-JBackbone=Qwen2.5-7B, Method Category=Hybrid2025.0992.25
MetaTuner-IBackbone=Qwen2.5-7B, Method Category=Hybrid2025.0992.15
BetterTogetherBackbone=Qwen2.5-7B, Method Category=Hybrid2025.0989.8
DPOBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0987.9
MetaTuner-JBackbone=Qwen2.5-3B, Method Category=Hybrid2025.0987.15
BetterTogetherBackbone=Qwen2.5-3B, Method Category=Hybrid2025.0986.6
MetaTuner-IBackbone=Qwen2.5-3B, Method Category=Hybrid2025.0986.55
KTOBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0985
CFPOBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0984.8
PPOBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0984.1
SFTBackbone=Qwen2.5-7B, Method Category=Fine-Tuning2025.0982.65
BPOBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0982.05
RLPromptBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0981.2
BPOBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0972.9
OPROBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0969.35
OPROBackbone=Qwen2.5-7B, Method Category=Prompt Optimization2025.0969.1
RLPromptBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0967.15
CFPOBackbone=Qwen2.5-3B, Method Category=Prompt Optimization2025.0964.2
DPOBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0961.2
KTOBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0958.7
PPOBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0952.25
SFTBackbone=Qwen2.5-3B, Method Category=Fine-Tuning2025.0952.05
Qwen2.5Backbone=Qwen2.5-7B, Method Category=Vanilla2025.0936.8
Qwen2.5Backbone=Qwen2.5-3B, Method Category=Vanilla2025.0925