List your company
ResearchFormerly WizWand

Knowledge-intensive generation on ELI5 (dev)

26.6ROUGE-L ScoreKID
15.6818.51521.3524.185Apr 6, 2022
Updated 8mo ago

Evaluation results

MethodLinks
KIDBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=fine-tuned, Decoding Strategy=KID2022.0426.627.9
KIDBackbone=BART-large, Parameters=406M, Evaluation Protocol=fine-tuned, Decoding Strategy=KID2022.0426.327.4
RAGRole=Published SotA2022.0426.2—
GPT2-mediumBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=fine-tuned, Decoding Strategy=Sampling2022.0425.423.8
BART-largeBackbone=BART-large, Parameters=406M, Evaluation Protocol=fine-tuned, Decoding Strategy=Sampling2022.0425.125.8
BART-largeBackbone=BART-large, Parameters=406M, Evaluation Protocol=fine-tuned, Decoding Strategy=Beam2022.0424.725.6
GPT2-mediumBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=fine-tuned, Decoding Strategy=Beam2022.0424.622.9
BART-largeBackbone=BART-large, Parameters=406M, Evaluation Protocol=zero-shot2022.0420.621.4
GPT2-mediumBackbone=GPT2-medium, Parameters=345M, Evaluation Protocol=zero-shot2022.0416.114.6