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

Question Answering on 2WikiQA (test)

57.9EM

Search-R1

14.42825.7143748.286Feb 11, 2026Mar 2, 2026Mar 21, 2026Apr 10, 2026Apr 29, 2026May 18, 2026Jun 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
57.964.9
2026.02
56.363.2
2026.02
47.755.2
2026.06
32.739.48
2026.06
27.334.3
2026.06
27.333.67
2026.06
26.233.12
2026.06
24.930.98
2026.06
24.931.61
2026.06
22.930.29
2026.06
22.927.13
2026.06
21.527.65
2026.06
20.727.45
2026.06
20.426.14
2026.06
20.426.26
2026.06
20.427.29
2026.06
20.126.32
2026.06
19.426.4
2026.06
18.825.33
2026.06
17.924.27
2026.06
17.924.04
2026.06
16.622.77
2026.06
16.323.13
2026.06
16.122.17