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

Faithfulness Evaluation on AG-news (test)

2Rate of Label Changes

LIME

-1.823.8549.575.15Mar 31, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.03
2
2026.03
3
2026.03
3.5
2026.03
4
2026.03
11.5
2026.03
13
2026.03
14
2026.03
15
2026.03
17.5
2026.03
20
2026.03
20.5
2026.03
23.5
2026.03
26.5
2026.03
28
2026.03
30
2026.03
41
2026.03
72.5
2026.03
73.5
2026.03
79
2026.03
79.5
2026.03
85
2026.03
90.5
2026.03
96
2026.03
97