List your company

Question Answering on HotpotQA (out-of-domain)

64.9PrecisionKP
30.0639.10548.1557.195Feb 2, 2026

Evaluation results

MethodLinks
KPBackbone=Gemma-2-9B2026.0264.942.451.3
VeriFY-NMBackbone=Gemma-2-9B2026.0261.869.665.5
VeriFY-MMBackbone=Gemma-2-9B2026.025680.766.1
SCBackbone=Gemma-2-9B2026.0255.979.365.6
VeriFY-SMBackbone=Gemma-2-9B2026.0254.381.965.3
KPBackbone=Gemma-2-2B2026.0251.74347
VeriFY-NMBackbone=Gemma-2-2B2026.0248.859.953.8
SCBackbone=Gemma-2-2B2026.0247.558.852.6
BaseBackbone=Gemma-2-9B2026.0244.2——
VeriFY-MMBackbone=Gemma-2-2B2026.0242.473.653.8
VeriFY-SMBackbone=Gemma-2-2B2026.0240.477.953.2
BaseBackbone=Gemma-2-2B2026.0231.4——