List your company
ResearchFormerly WizWand

Fact Verification on FEVER (test)

79.47LA ScoreProoFVer-SB
64.899668.682372.46576.2477Jul 22, 2019Mar 30, 2020Dec 8, 2020Aug 18, 2021Apr 27, 2022Jan 5, 2023Sep 15, 2023
Updated 8mo ago

Evaluation results

MethodLinks
ProoFVer-SBRetriever=Stammbach (2021)2021.0879.4776.82——
ProoFVerRetriever=Liu et al. (2020)2021.0879.2574.37——
DominikSRetriever=Stammbach (2021)2021.0879.1676.78——
ProoFVer-ARetriever=Liu et al. (2020)2021.0877.1672.47——
DREAMBackbone=XLNet-Large2023.0976.85———
DOMLIN++Backbone=RoBERTa-Large2023.0976.6———
CorefBERTRetriever=Liu et al. (2020)2021.0875.9672.3——
ROBERTaBase Flexible (IE1) + MSPP (REk)Backbone=RoBERTa-Base, Sequence Type=Flexible, Prediction Head=IE1, MSPP Pre-training=REk2023.0975.36———
Joint Pre IEk + FT IE1Pre-training head=IEk, Fine-tuning head=IE12022.0574.39———
ROBERTaBase Fixed (IE1) + MSPP (IEk)Backbone=RoBERTa-Base, Sequence Type=Fixed, Prediction Head=IE1, MSPP Pre-training=IEk2023.0974.39———
Joint Pre IEk + FT AE1Pre-training head=IEk, Fine-tuning head=AE12022.0574.25———
ProoFVer-MVRetriever=Liu et al. (2020)2021.0874.1870.09——
Joint Pre AEk + FT AE1Pre-training head=AEk, Fine-tuning head=AE12022.0574.13———
ROBERTaBase Fixed (AE1) + MSPP (AEk)Backbone=RoBERTa-Base, Sequence Type=Fixed, Prediction Head=AE1, MSPP Pre-training=AEk2023.0974.13———
KGATBackbone=RoBERTa-Base2022.0574.07———
KGATRetriever=Liu et al. (2020)2021.0874.0770.38——
KGAT with RoBERTaBaseBackbone=RoBERTa-Base2023.0974.07———
Joint Pre AEk + FT IE1Pre-training head=AEk, Fine-tuning head=IE12022.0573.77———
Joint RoBERTa-Base + FT IE1Approach=Joint, Backbone=RoBERTa-Base, Fine-tuning head=IE12022.0573.56———
ROBERTaBase Flexible (IE1)Backbone=RoBERTa-Base, Sequence Type=Flexible, Prediction Head=IE1, MSPP Pre-training=false2023.0973.56———
ROBERTaBase Fixed (IE1)Backbone=RoBERTa-Base, Sequence Type=Fixed, Prediction Head=IE1, MSPP Pre-training=false2023.0973.01———
ROBERTaBase Fixed (AE1)Backbone=RoBERTa-Base, Sequence Type=Fixed, Prediction Head=AE1, MSPP Pre-training=false2023.0972.94———
Transformer-XH2022.0572.39———
Transformer-XH2023.0972.39———
GEAR2019.0771.667.1——
GEAR2022.0571.6———
GEAR2023.0971.6———
BERT Concat2019.0771.0165.64——
BERT Pair2019.0769.7565.18——
UNC NLP2019.0768.2164.21——
UCL MRG2019.0767.6262.52——
Athene2019.0765.4661.58——
ATLASshots=15-shot, approach=fine-tuning2022.08——56.2—
ATLASshots=65-shot, approach=fine-tuning2022.08——64.3—
ATLASshots=Full dataset, approach=fine-tuning2022.08——78—
ATLASshots=Full dataset, approach=fine-tuning, index=FEVER Wikipedia corpus2022.08——80.1—
DiffuTruth2026.02———64
Direct NLI2026.02———71
DOMLIN++Retrieval Type=sophisticated2022.05——76.6—
DREAMBackbone=XL-Net, Retrieval Type=sophisticated2022.05——76.85—
FTK=16, backbone=RoBERTa, protocol=few-shot2023.06——36.1—
GEAR2022.05——71.6—
Gophershots=15-shot, approach=prompting2022.08——51.1—
HOK=16, backbone=RoBERTa, protocol=few-shot2023.06——20.2—
Hybrid2026.02———72.5
Joint BERT-BaseBackbone=BERT-Base, Model Architecture=Joint2022.05——71.01—
Joint Pre AEk + FT AE1Backbone=RoBERTa-Base, Model Architecture=Joint, Pre-training Head=AEk, Fine-tuning Head=AE12022.05——74.13—
Joint Pre AEk + FT IE1Backbone=RoBERTa-Base, Model Architecture=Joint, Pre-training Head=AEk, Fine-tuning Head=IE12022.05——73.77—
Joint Pre IEk + FT AE1Backbone=RoBERTa-Base, Model Architecture=Joint, Pre-training Head=IEk, Fine-tuning Head=AE12022.05——74.25—
Joint Pre IEk + FT IE1Backbone=RoBERTa-Base, Model Architecture=Joint, Pre-training Head=IEk, Fine-tuning Head=IE12022.05——74.39—
Joint RoBERTa-BaseBackbone=RoBERTa-Base, Model Architecture=Joint, Fine-tuning Head=IE12022.05——73.56—
KGATBackbone=RoBERTa-Base2022.05——74.07—
LOK=16, backbone=RoBERTa, protocol=few-shot2023.06——22.6—
MixDAK=16, backbone=RoBERTa, protocol=few-shot2023.06——32.6—
Pairwise BERT-BaseBackbone=BERT-Base, Model Architecture=Pairwise2022.05——69.75—
PFK=16, backbone=RoBERTa, protocol=few-shot2023.06——27.4—
ProoFVershots=Full dataset2022.08——79.5—
PTK=16, backbone=RoBERTa, protocol=few-shot2023.06——31.1—
Transformer-XH2022.05——72.39—