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

Multilingual Question Answering on TyDiQA (1-shot macro-averaged)

48.86F1 Score (1-shot macro)

Filter-then-Weight

11.243221.009130.77540.5409Mar 8, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.03
48.86
2026.03
48.67
2026.03
47.5
2026.03
47.21
2026.03
47.16
2026.03
47.01
2026.03
47.01
2026.03
46.88
2026.03
46.29
2026.03
45.35
2026.03
45.25
2026.03
45.17
2026.03
45.07
2026.03
44.82
2026.03
44.23
2026.03
44.15
2026.03
43.65
2026.03
43.57
2026.03
43.14
2026.03
43.07
2026.03
42.7
2026.03
42.47
2026.03
41.14
2026.03
38.68
2026.03
20.94
2026.03
20.94
2026.03
12.69
2026.03
12.69