Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

2Wiki

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question Answering2WIKI
EM86
260
Multi-hop Question Answering2Wiki
Exact Match74.9
215
Question Answering2Wiki (test)
EM Accuracy61.8
59
Class-level Continual Learning2Wiki
Average Accuracy (AA)71.74
56
Multi-Hop Question Answering2Wiki
Accuracy (2Wiki)43.6
44
Multi-hop QA2Wiki
EM62
42
Retrieval2Wiki
Recall@596.13
42
Multi-hop Question Answering2Wiki (test)
F1 Score69.7
34
Multi-hop QA Retrieval2Wiki
Recall@290.1
32
Adversarial Attack2Wiki
ASR78.8
30
Multi-Hop Question Answering2Wiki (out-of-domain)
Accuracy47.6
28
Question Answering2Wiki 100K context
Accuracy78.91
25
Multi-Hop Question Answering2Wiki (test)
Accuracy45.1
24
Multi-Hop Search-augmented Question Answering2Wiki
Success Rate45.2
22
Multi-hop Question Answering2Wiki 18
Exact Match (EM)43.6
20
Multi-Hop Question Answering2Wiki
Token-Level F158.7
20
Question Answering2Wiki 30K context
Accuracy73.7
19
Question Answering2Wiki 10K context
Accuracy72.2
19
Multi-hop Question Answering2Wiki
pass@158
18
Multi-Hop Question Answering2Wiki
Exact Match (EM)46.9
18
Multi-Hop Question Answering2wiki
F1 Score61.3
17
Multi-Hop QA2Wiki
Accuracy70.5
17
Multi-hop Question Answering2Wiki
MBE59
17
Multi-hop Question Answering2Wiki
EM48.89
16
Multi-Hop QA Verification2wiki
P@181.21
16
Showing 25 of 80 rows