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

Natural Language Inference on ANLI R1 1.0 (test)

41.1Weighted F1

Label-Guided Explanation Selection

15.72422.31228.935.488Dec 18, 2024
Updated 3mo ago

Evaluation Results

MethodLinks
2024.12
41.1
2024.12
40.2
2024.12
40
2024.12
39.3
2024.12
39.3
2024.12
35.7
2024.12
35.1
2024.12
35
2024.12
34.1
2024.12
33.9
2024.12
31.7
2024.12
31.4
2024.12
30.9
2024.12
30.5
2024.12
30.4
2024.12
30.2
2024.12
29.6
2024.12
29.2
2024.12
29.2
2024.12
28.5
2024.12
28.4
2024.12
26.8
2024.12
25.8
2024.12
24.6
2024.12
22.9
2024.12
22
2024.12
17
2024.12
16.7