List your company

Symbolic Reasoning on AQUA

80.3AccuracyCOT
37.55648.65359.7570.847Feb 18, 2025

Evaluation results

MethodLinks
COTBackbone=Qwen2-7B, Protocol=Annotation Tuning2025.0280.3
COTBackbone=Qwen2-7B, Protocol=ICL2025.0279.1
QuaSARBackbone=Llama-3-8B, Protocol=Annotation Tuning2025.0278.4
QuaSARBackbone=Qwen2-7B, Protocol=Annotation Tuning2025.0278.3
QuaSARBackbone=Qwen2-7B, Protocol=ICL2025.0272.6
COMATBackbone=Qwen2-7B, Protocol=ICL2025.0272.4
COTBackbone=Llama-3-8B, Protocol=Annotation Tuning2025.0272.2
COTBackbone=Llama-3-8B, Protocol=ICL2025.0269.6
Llama-3-8BStrategy=Base, Protocol=Annotation Tuning2025.0267.3
QuaSARBackbone=Llama-3-8B, Protocol=ICL2025.0267.2
Llama-3-8BStrategy=Base, Protocol=ICL2025.0265.2
Qwen2-7BStrategy=Base, Protocol=Annotation Tuning2025.0263.7
FLAREBackbone=Llama-3-8B, Protocol=ICL2025.0262.9
Qwen2-7BStrategy=Base, Protocol=ICL2025.0262.9
QuaSARBackbone=Qwen2-1.5B, Protocol=Annotation Tuning2025.0262.2
COTBackbone=Qwen2-1.5B, Protocol=Annotation Tuning2025.0259.9
COTBackbone=Qwen2-1.5B, Protocol=ICL2025.0258.7
QuaSARBackbone=Qwen2-1.5B, Protocol=ICL2025.0257.6
Qwen2-1.5BStrategy=Base, Protocol=Annotation Tuning2025.0257.2
Qwen2-1.5BStrategy=Base, Protocol=ICL2025.0256.8
QuaSARBackbone=Llama-3-1B, Protocol=Annotation Tuning2025.0255.4
COTBackbone=Llama-3-1B, Protocol=Annotation Tuning2025.0252
QuaSARBackbone=Llama-3-1B, Protocol=ICL2025.0251.6
COTBackbone=Llama-3-1B, Protocol=ICL2025.0250.7
Llama-3-1BStrategy=Base, Protocol=Annotation Tuning2025.0240.3
Llama-3-1BStrategy=Base, Protocol=ICL2025.0239.2