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

Question Answering on SQuAD (F1, Subspan EM, EM Count)

71.4F1 Score

Results with Original Prompts

24.142436.411248.6860.9488Sep 19, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.09
71.499.932,80547.49
2024.09
69.6299.922,73646.32
2024.09
68.0399.92,63744.64
2024.09
65.8499.922,59243.88
2024.09
62.7999.812,41240.83
2024.09
62.7199.862,23137.77
2024.09
62.799.832,24638.02
2024.09
61.799.882,38640.39
2024.09
58.3799.712,19537.16
2024.09
57.9299.762,19937.23
2024.09
56.6799.782,07635.14
2024.09
55.4699.812,06734.99
2024.09
54.5799.782,02434.26
2024.09
53.1199.581,83831.12
2024.09
52.8699.661,84831.28
2024.09
51.5699.641,86731.61
2024.09
51.3998.682,04234.57
2024.09
46.3798.261,81330.69
2024.09
46.3799.271,54826.21
2024.09
46.2599.311,63627.7
2024.09
46.1599.611,54526.16
2024.09
41.9799.121,39123.55
2024.09
41.4999.411,36323.07
2024.09
40.3597.91,55526.32
2024.09
39.8599.171,34222.72
2024.09
38.7899.271,25921.31
2024.09
38.7498.981,26821.47
2024.09
37.3797.831,41723.99
2024.09
36.6298.871,10818.76
2024.09
35.5397.821,32322.4
2024.09
35.298.971,16719.76
2024.09
31.9898.931,01117.12
2024.09
30.5797.8597416.49
2024.09
28.2797.5891815.54
2024.09
26.9697.2686614.66
2024.09
25.9697.1484814.36