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

Contextual Robustness Question Answering on ConflictQA Unknown queries

99.28Accuracy (Short Context)

COT

71.82478.95286.0893.208Feb 19, 2025
Updated 5mo ago

Evaluation Results

MethodLinks
2025.02
99.2896.28
2025.02
98.3295.23
2025.02
98.2397.03
2025.02
97.396.99
2025.02
97.2797.09
2025.02
96.8997.52
2025.02
96.8595.72
2025.02
96.2993.08
2025.02
96.197.69
2025.02
95.9997.49
2025.02
95.5289.79
2025.02
95.3897.51
2025.02
95.2694.39
2025.02
94.3296.03
2025.02
92.3690.17
2025.02
92.0991.05
2025.02
91.1889.07
2025.02
89.3398.08
2025.02
89.0388.36
2025.02
81.6681.46
2025.02
80.8192
2025.02
72.8886.73