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

Question Answering on HotpotQA (out-of-domain)

64.9Precision

KP

30.0639.10548.1557.195Feb 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
64.942.451.3
2026.02
61.869.665.5
2026.02
5680.766.1
2026.02
55.979.365.6
2026.02
54.381.965.3
2026.02
51.74347
2026.02
48.859.953.8
2026.02
47.558.852.6
2026.02
44.2--
2026.02
42.473.653.8
2026.02
40.477.953.2
2026.02
31.4--