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

Contextual Robustness Question Answering on ConflictQA (Known queries)

82.49Accuracy (Contradictory Short)

Grft-requery

18.613235.196651.7868.3634Feb 19, 2025
Updated 5mo ago

Evaluation Results

MethodLinks
2025.02
82.4988.1597.6898.4699.38
2025.02
69.4778.1882.0296.0399.71
2025.02
60.8861.1973.2268.8699.07
2025.02
60.4245.3972.9967.794.13
2025.02
59.646.772.5669.893.6
2025.02
54.1152.2570.8666.3698.04
2025.02
53.4446.5569.873.6694.5
2025.02
41.8336.0242.6836.2599.04
2025.02
41.0536.4872.368.0998.14
2025.02
40.0843.0562.0369.0193.02
2025.02
39.3344.0763.0668.8595.9
2025.02
36.3635.0259.1947.0898.37
2025.02
35.4825.5653.6844.8591.87
2025.02
34.5525.3353.1444.6299.26
2025.02
32.6826.9454.0847.2895.29
2025.02
32.0830.1826.0925.8993.28
2025.02
31.9829.0227.1924.9695.03
2025.02
31.6827.4252.2147.2597.68
2025.02
30.8126.08191999.57
2025.02
29.1927.8925.3124.7897.66
2025.02
26.4726.9951.6739.6299.67
2025.02
21.0723.0122.7724.9480.79