Fact Verification on KILT: FEVER

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	Re2G	89.55	No	Re2G: Retrieve, Rerank, Generate	2022-07-13	Code
2	intersect	89.54	No	-	-	-
3	Sphere	89.12	No	-	-	-
4	Wikipedia	88.99	No	-	-	-
5	aa_evalai	88.45	No	-	-	-
6	BART + DPR	86.74	No	-	-	-
7	Multitask DPR + BART	86.32	No	-	-	-
8	RAG	86.31	No	KILT: a Benchmark for Knowledge Intensive Langua...	2020-09-04	Code
9	KGI	85.58	No	-	-	-
10	BART	78.93	No	-	-	-
11	T5-base	76.3	No	KILT: a Benchmark for Knowledge Intensive Langua...	2020-09-04	Code
12	GENRE+roBERTa finetuning	76.26	No	-	-	-
13	SVM with rbf kernel	72.34	No	-	-	-
14	ElefPav	71.58	No	-	-	-
15	Alessandro_Tansel	71.42	No	-	-	-
16	JuanTran	71.38	No	-	-	-
17	Logistic Regression	71.24	No	-	-	-
18	QDA	71.12	No	-	-	-
19	SVM	70.71	No	-	-	-
20	stupidTeam	69.71	No	-	-	-
21	BERT + DPR	69.68	No	-	-	-
22	QDA_EMB2	69.41	No	-	-	-
23	SVM	68.43	No	-	-	-
24	Marco Aurelio Sterpa	67.98	No	-	-	-
25	NSMN	66.1	No	-	-	-
26	its_all_greek_to_me	61.6	No	-	-	-
27	multi-task small	33.58	No	-	-	-
28	LogisticRegression	23.01	No	-	-	-
29	galimaldo	12.57	No	-	-	-
30	TABi	0	No	-	-	-
31	chriskuei	0	No	-	-	-
32	GENRE	0	No	-	-	-
33	Multi-task DPR	0	No	-	-	-