Natural Language Inference on E-SNLI

91.31Accuracy

ColD-Fusion

Updated 3mo ago

Evaluation Results

Method	Links
ColD-Fusion 2022.12		91.31
Multitask 2022.12		91.27
Finetune 2022.12		91
DSS 2024.03		89.51
MI-based distillation 2024.03		89.5
Single-task 2024.03		88.88
Self-consistency 2022.03		88.4
Finetuning 2024.03		88.38
Standard-prompting (no-rationale) 2022.03		85.8
CoT-prompting 2022.03		81
text-davinci-002 2022.05		75.6
text-davinci-002 2022.05		69.4
text-davinci-002 2022.05		69.1
P-E+EXPLCAL 2022.05		68.5
P-E+EXPLCAL 2022.05		67.6
P-E+ZHANG 2022.05		65.9
P-E+EXPLCAL 2022.05		65.8
P-E+PROBCAL 2022.05		65.4
P-E+PROBCAL 2022.05		65.4
P-E+PROBCAL 2022.05		65.4
P-E+ZHANG 2022.05		65.4
P-E+ZHANG 2022.05		65.2
P-E+PROBCAL 2022.05		64.4
P-E+EXPLCAL 2022.05		64.2
FEW-SHOT+PROBCAL 2022.05		63.9
FEW-SHOT+PROBCAL 2022.05		63.2
P-E+ZHANG 2022.05		63
FEW-SHOT+PROBCAL 2022.05		62.4
FEW-SHOT+PROBCAL 2022.05		61.9
P-E 2022.05		59.4
InstructGPT 2022.05		59.4
FEW-SHOT(NN) 2022.05		58.9
FEW-SHOT 2022.05		56.8
InstructGPT 2022.05		56.8
ROBERTa 2022.05		54.9
MUPPET 2022.12		52.59
ROBERTa 2022.05		49
GPT-3 2022.05		48.7
OPT (175B) 2022.05		44
OPT (175B) 2022.05		43.4
GPT-3 2022.05		43.3
ROBERTa 2022.05		43
InstructGPT 2022.05		41.8
GPT-3 2022.05		40.4
ROBERTa 2022.05		40.1
OPT (175B) 2022.05		39.3