List your company
ResearchFormerly WizWand

Multi-hop Reasoning on CommaQA-E compositional

80.8Exact MatchChatGPT (SKiC)
13.7231.13548.5565.965Aug 1, 2023
Updated 8mo ago

Evaluation results

MethodLinks
ChatGPT (SKiC)Model=ChatGPT, Prompting=SKiC†, #-shots=22023.0880.8
text-davinci-003 (SKiC)Model=text-davinci-003, Prompting=SKiC†, #-shots=22023.0874.8
ChatGPT (Decomp)Model=ChatGPT, Prompting=Decomp, #-shots=122023.0873.5
text-davinci-003 (Decomp)Model=text-davinci-003, Prompting=Decomp, #-shots=122023.0866.6
LLAMA-65B (SKiC)Model=LLAMA-65B, Prompting=SKiC†, #-shots=22023.0852
ChatGPT (CoT)Model=ChatGPT, Prompting=CoT, #-shots=42023.0846.4
LLAMA-65B (Decomp)Model=LLAMA-65B, Prompting=Decomp, #-shots=122023.0840.4
ChatGPT (4-shots)Model=ChatGPT, Prompting=4-shots, #-shots=42023.0840.3
text-davinci-003 (CoT)Model=text-davinci-003, Prompting=CoT, #-shots=42023.0838.2
text-davinci-003 (4-shots)Model=text-davinci-003, Prompting=4-shots, #-shots=42023.0833.5
LLAMA-65B (CoT)Model=LLAMA-65B, Prompting=CoT, #-shots=42023.0830.8
ChatGPT (zero-shot)Model=ChatGPT, Prompting=zero-shot, #-shots=02023.0830.6
text-davinci-003 (zero-shot)Model=text-davinci-003, Prompting=zero-shot, #-shots=02023.0826.8
LLAMA-65B (4-shots)Model=LLAMA-65B, Prompting=4-shots, #-shots=42023.0824.6
LLAMA-65B (zero-shot)Model=LLAMA-65B, Prompting=zero-shot, #-shots=02023.0816.3