List your company

Logic reasoning on Causal Judgement

36AccuracySelf-discover
-0.32729.103918.53527.9661Sep 30, 2024

Evaluation results

MethodLinks
Self-discoverBackbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0936
IAP-mvBackbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0929.95
Prompt #5Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0928.34
AMV (#1-7)Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0927.5
IAP-ssBackbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0926.74
AMV (all)Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0926.1
OPPRBackbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0919.79
IAP-mvBackbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0919.25
OPPRBackbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0918.18
AMV (#1-7)Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0918.13
Prompt #2Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.0917.11
AMV (all)Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0917.06
IAP-ssBackbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0916.57
Prompt #8Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0916.04
Prompt #2Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0914.97
Prompt #4Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0913.9
Prompt #3Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0912.3
Self-discoverBackbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.0911.23
Prompt #3Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.099.63
Prompt #1Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.099.09
Prompt #4Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.096.95
Prompt #5Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.095.35
Prompt #1Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.094.28
Prompt #6Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.093.74
Prompt #6Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.093.21
Prompt #9Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.092.67
Prompt #7Backbone=LLaMA-3-8B-Instruct, Zero-shot CoT=true2024.092.14
Prompt #9Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.092.14
Prompt #7Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.091.07
Prompt #8Backbone=Qwen-14B-Chat, Zero-shot CoT=true2024.091.07