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

Span-level Hallucination Detection on RagTruth-Avg (test)

76.63F1 Score

Fourier-high

67.103669.576872.0574.5232Feb 20, 2026
Updated 4mo ago

Evaluation Results

MethodLinks
2026.02
76.6388.12
2026.02
75.9787.42
2026.02
75.5487.64
2026.02
73.2284.95
2026.02
70.6385.85
2026.02
70.0384.12
2026.02
69.5384.48
2026.02
69.1181.17
2026.02
68.1980.39
2026.02
67.8181.83
2026.02
67.7378.84
2026.02
67.4778.77