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

Evidence Retrieval on FAKEWIKI RolePlay

63.8Recall@10

SCORINGMODEL

-2.44814.75131.9549.149May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
63.8
2026.05
63.4
2026.05
60.5
2026.05
43.5
2026.05
40.3
2026.05
30.6
2026.05
29.1
2026.05
27.5
2026.05
26.2
2026.05
26
2026.05
23.6
2026.05
23.5
2026.05
22.3
2026.05
21.6
2026.05
20.3
2026.05
19.9
2026.05
16.1
2026.05
11.7
2026.05
11.3
2026.05
10.6
2026.05
9.7
2026.05
9.3
2026.05
0.1
2026.05
0.1
2026.05
0.1
2026.05
0.1