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

Open-domain Question Answering on HotpotQA in-domain

72.4F1 Score

Search-R1

-2.6370416.8437336.324555.80527Aug 8, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.08
72.478.8
2025.08
71.878
2025.08
71.279.4
2025.08
70.978.8
2025.08
70.876.8
2025.08
70.178.8
2025.08
7077.6
2025.08
67.776
2025.08
65.973.6
2025.08
64.373.4
2025.08
63.169.2
2025.08
59.669.6
2025.08
5964.2
2025.08
53.859.2
2025.08
5359.4
2025.08
50.961.6
2025.08
50.657
2025.08
49.262.8
2025.08
47.554.4
2025.08
46.551.2
2025.08
4650.4
2025.08
4550.4
2025.08
44.548.8
2025.08
4350.8
2025.08
42.745.8
2025.08
37.940.6
2025.08
36.437.6
2025.08
33.847.2
2025.08
30.132.2
2025.08
28.861
2025.08
28.631.6
2025.08
26.627.2
2025.08
24.931
2025.08
0.7240.788
2025.08
0.7180.78
2025.08
0.7120.794
2025.08
0.7090.788
2025.08
0.7080.768
2025.08
0.7010.788
2025.08
0.70.776
2025.08
0.6770.76
2025.08
0.6590.736
2025.08
0.6540.75
2025.08
0.6310.692
2025.08
0.590.642
2025.08
0.5690.642
2025.08
0.5450.744
2025.08
0.5310.74
2025.08
0.5060.57
2025.08
0.4920.628
2025.08
0.4750.544
2025.08
0.460.504
2025.08
0.4370.592
2025.08
0.4270.458
2025.08
0.2860.316
2025.08
0.2660.272
2025.08
0.2490.31