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

Hallucination Detection on RAGTruth RT-QA 1.0 (test)

0.7885F1 Score

Fourier-high

0.264860.4008050.536750.672695Feb 20, 2026Mar 9, 2026Mar 26, 2026Apr 13, 2026Apr 30, 2026May 17, 2026Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
0.78850.9099
2026.02
0.78760.9117
2026.02
0.78320.9148
2026.02
0.7810.9083
2026.02
0.78070.9049
2026.02
0.72770.8584
2026.02
0.71940.8526
2026.02
0.71070.8449
2026.02
0.70680.8792
2026.02
0.70290.8741
2026.02
0.69470.8727
2026.02
0.6930.8482
2026.02
0.69090.865
2026.02
0.68340.8552
2026.02
0.68320.8481
2026.02
0.65510.7084
2026.02
0.62890.6942
2026.02
0.6270.7357
2026.02
0.61440.6121
2026.02
0.60290.6425
2026.02
0.59720.6364
2026.02
0.59280.5893
2026.02
0.59140.5865
2026.02
0.5740.6457
2026.02
0.56360.7497
2026.02
0.56360.7497
2026.02
0.49790.5253
2026.02
0.49040.4611
2026.02
0.48070.6147
2026.02
0.47880.4734
2026.06
0.2960.589
2026.06
0.2890.557
2026.06
0.2850.556