List your company

Instruction Following on ComplexInstruct Level 2

94.6ISRDVRws
53.72864.33974.9585.561Oct 16, 2024

Evaluation results

MethodLinks
DVRwsBackbone=Llama-3.1-70B-Instruct-AWQ-INT4, warm-start=true2024.1094.6
DVRcsBackbone=Llama-3.1-70B-Instruct-AWQ-INT4, cold-start=true2024.1094.3
CRITICBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1093.2
ReActBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1091
R-SampleBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1090.8
DVRBackbone=Llama3.1-8B, Evaluation Protocol=zero-shot2024.1088.7
DVR_WSBackbone=Llama-3.1-8B-Instruct, Refinement Repository=warm-start2024.1088.7
GPT-4-turboEvaluation Protocol=zero-shot2024.1088.4
DVR_CSBackbone=Llama-3.1-8B-Instruct, Refinement Repository=cold-start2024.1087.9
DVRBackbone=Llama-3-8B-Instruct, Start Type=Warm-Start2024.1087.6
CRITICBackbone=Llama-3.1-8B-Instruct2024.1087.1
DVRBackbone=Llama-3-8B-Instruct, Start Type=Cold-Start2024.1086.7
R-SampleBackbone=Llama-3.1-8B-Instruct2024.1086.7
ReActBackbone=Llama-3.1-8B-Instruct2024.1086.1
CRITICBackbone=Llama-3-8B-Instruct2024.1085.8
BSMBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1084.5
VanillaBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1083.7
ReflexionBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1083.5
U-SCBackbone=Llama-3.1-70B-Instruct-AWQ-INT42024.1083.3
DVRBackbone=Mistral-7B, Evaluation Protocol=zero-shot2024.1081.3
ReActBackbone=Llama-3-8B-Instruct2024.1081.3
R-SampleBackbone=Llama-3-8B-Instruct2024.1080.9
ReflxionBackbone=Llama-3.1-8B-Instruct2024.1078.1
Llama3.1-8BEvaluation Protocol=zero-shot2024.1076.6
VanillaBackbone=Llama-3.1-8B-Instruct2024.1076.6
U-SCBackbone=Llama-3.1-8B-Instruct2024.1076.3
BSMBackbone=Llama-3.1-8B-Instruct2024.1075.3
ReflexionBackbone=Llama-3-8B-Instruct2024.1072.1
BSMBackbone=Llama-3-8B-Instruct2024.1071.9
U-SCBackbone=Llama-3-8B-Instruct2024.1071.8
VanillaBackbone=Llama-3-8B-Instruct2024.1071.7
Mistral-7BEvaluation Protocol=zero-shot2024.1055.3