HyperAIHyperAI

Command Palette

Search for a command to run...

Fact Verification On Kilt Fever

Metrics

Accuracy
KILT-AC
R-Prec
Recall@5

Results

Performance results of various models on this benchmark

Paper Title
Re2G89.5578.5388.9292.52Re2G: Retrieve, Rerank, Generate
intersect89.5471.2881.4589.56-
Sphere89.120.00.00.0-
Wikipedia88.9965.6874.7787.89-
aa_evalai88.450.00.00.0-
BART + DPR86.7447.6855.3374.29-
Multitask DPR + BART86.3263.9474.4887.52-
RAG86.3153.4561.9475.55KILT: a Benchmark for Knowledge Intensive Language Tasks
KGI85.5864.4175.684.95-
BART78.930.00.00.0-
T5-base76.30.00.00.0KILT: a Benchmark for Knowledge Intensive Language Tasks
GENRE+roBERTa finetuning76.260.00.00.0-
SVM with rbf kernel72.340.00.00.0-
ElefPav71.580.00.00.0-
Alessandro_Tansel71.420.00.00.0-
JuanTran71.380.00.00.0-
Logistic Regression71.240.00.00.0-
QDA71.120.00.00.0-
SVM70.710.00.00.0-
stupidTeam69.710.00.00.0-
0 of 33 row(s) selected.
Fact Verification On Kilt Fever | SOTA | HyperAI