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

Short-text Multi-doc Question Answering on RGB noise robustness testbed (test)

96EM (Noise 0)

Our model (PAM QA)

86.296888.815991.33593.8541Nov 15, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
9690.679085.567.33
95.6794.679187.6770.67
94.67928885.369.67
9390.338982.3363.33
2023.11
91.67908984.6766.33
86.6782.3376.6772.3354