List your company
ResearchFormerly WizWand

Relational Reasoning on Chinese Kinship

71.2AccuracyPoT-LLM
18.47232.16145.8559.539Dec 23, 2024
Updated 7mo ago

Evaluation results

MethodLinks
PoT-LLMLLM=GPT-4o, Category=Prompting-based2024.1271.2
CoTLLM=GPT-4o, Category=Prompting-based2024.1268.5
CoT-SCLLM=GPT-4o, Category=Prompting-based2024.1268.5
Zero-shotLLM=GPT-4o, Category=Prompting-based2024.1267.1
Few-shotLLM=GPT-4o, Category=Prompting-based2024.1265.8
PoT-LLMLLM=GPT-4-turbo, Category=Prompting-based2024.1253.4
CoT-SCLLM=GPT-4-turbo, Category=Prompting-based2024.1246.6
Zero-shotLLM=GPT-4-turbo, Category=Prompting-based2024.1245.2
CoTLLM=GPT-4-turbo, Category=Prompting-based2024.1239.7
Few-shotLLM=GPT-4-turbo, Category=Prompting-based2024.1237
Few-shotLLM=Llama3-70B, Category=Prompting-based2024.1235.6
PoT-LLMLLM=Llama3-70B, Category=Prompting-based2024.1235.6
Zero-shotLLM=Llama3-70B, Category=Prompting-based2024.1231.5
PoT-LLMLLM=GPT-3.5-turbo, Category=Prompting-based2024.1227.4
CoTLLM=Llama3-70B, Category=Prompting-based2024.1227.4
CoT-SCLLM=Llama3-70B, Category=Prompting-based2024.1227.4
CoT-SCLLM=GPT-3.5-turbo, Category=Prompting-based2024.1224.7
Few-shotLLM=GPT-3.5-turbo, Category=Prompting-based2024.1223.3
CoTLLM=GPT-3.5-turbo, Category=Prompting-based2024.1221.9
Zero-shotLLM=GPT-3.5-turbo, Category=Prompting-based2024.1220.5