List your company
ResearchFormerly WizWand

Multi-hop Reasoning on CommaQA-E (test)

70Exact MatchChatGPT (SKiC)
9.6825.344156.66Aug 1, 2023
Updated 8mo ago

Evaluation results

MethodLinks
ChatGPT (SKiC)Model=ChatGPT, Prompting=SKiC†, #-shots=22023.0870
text-davinci-003 (SKiC)Model=text-davinci-003, Prompting=SKiC†, #-shots=22023.0866
ChatGPT (Decomp)Model=ChatGPT, Prompting=Decomp, #-shots=122023.0864
text-davinci-003 (Decomp)Model=text-davinci-003, Prompting=Decomp, #-shots=122023.0858
ChatGPT (CoT)Model=ChatGPT, Prompting=CoT, #-shots=42023.0855
ChatGPT (4-shots)Model=ChatGPT, Prompting=4-shots, #-shots=42023.0847
LLAMA-65B (SKiC)Model=LLAMA-65B, Prompting=SKiC†, #-shots=22023.0844
text-davinci-003 (CoT)Model=text-davinci-003, Prompting=CoT, #-shots=42023.0844
text-davinci-003 (4-shots)Model=text-davinci-003, Prompting=4-shots, #-shots=42023.0842
ChatGPT (zero-shot)Model=ChatGPT, Prompting=zero-shot, #-shots=02023.0842
text-davinci-003 (zero-shot)Model=text-davinci-003, Prompting=zero-shot, #-shots=02023.0834
LLAMA-65B (Decomp)Model=LLAMA-65B, Prompting=Decomp, #-shots=122023.0832
LLAMA-65B (CoT)Model=LLAMA-65B, Prompting=CoT, #-shots=42023.0827
LLAMA-65B (4-shots)Model=LLAMA-65B, Prompting=4-shots, #-shots=42023.0815
LLAMA-65B (zero-shot)Model=LLAMA-65B, Prompting=zero-shot, #-shots=02023.0812