List your company

Hierarchical Table Question Answering on MultiHiertt (test)

70.32AccuracyEEDP
-1.211217.359435.9354.5006Feb 17, 2024

Evaluation results

MethodLinks
EEDPBackbone=GPT-42024.0270.32
Program-of-Thoughts (PoT)Backbone=GPT-42024.0267.23
Chain-of-Thought (CoT)Backbone=GPT-42024.0255.13
Program-of-Thoughts (PoT)Backbone=GPT-3.5-Turbo2024.0252.18
EEDPBackbone=GPT-3.5-Turbo2024.0249.65
Chain-of-Thought (CoT)Backbone=GPT-3.5-Turbo2024.0242.33
DirectBackbone=GPT-42024.0241.35
EEDPBackbone=PaLM 2-540B2024.0237.97
DecomposersBackbone=GPT-42024.0236.86
Program-of-Thoughts (PoT)Backbone=PaLM 2-540B2024.0236.52
Chain-of-Thought (CoT)Backbone=Llama 2-13B2024.0230.66
DirectBackbone=GPT-3.5-Turbo2024.0225.88
EEDPBackbone=Llama 2-13B2024.0224.15
Chain-of-Thought (CoT)Backbone=Mistral-7B2024.0222.92
Chain-of-Thought (CoT)Backbone=PaLM 2-540B2024.0220.67
DecomposersBackbone=GPT-3.5-Turbo2024.0220.61
DecomposersBackbone=PaLM 2-540B2024.0220.19
Chain-of-Thought (CoT)Backbone=MAmmoTH-13B2024.0218.56
EEDPBackbone=MAmmoTH-13B2024.0218.36
Program-of-Thoughts (PoT)Backbone=Llama 2-13B2024.0218.12
DecomposersBackbone=Llama 2-13B2024.0216.86
Program-of-Thoughts (PoT)Backbone=Mistral-7B2024.0214.94
DirectBackbone=PaLM 2-540B2024.0214.2
DirectBackbone=Mistral-7B2024.0214.09
DecomposersBackbone=MAmmoTH-13B2024.0211.87
DecomposersBackbone=Mistral-7B2024.0211.63
EEDPBackbone=Mistral-7B2024.0210.97
DirectBackbone=MAmmoTH-13B2024.0210.12
Program-of-Thoughts (PoT)Backbone=MAmmoTH-13B2024.026.57
DirectBackbone=Llama 2-13B2024.021.54