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

Hallucination Detection on RAGTruth & HalluRAG Overall Average 1.0 (test)

0.7284Average F1 Score

Wavelet-high

0.4653840.5336670.601950.670233Feb 20, 2026
Updated 4mo ago

Evaluation Results

MethodLinks
2026.02
0.72840.8595
2026.02
0.72660.8532
2026.02
0.72140.8478
2026.02
0.71970.8494
2026.02
0.70530.8297
2026.02
0.67230.8198
2026.02
0.66870.8131
2026.02
0.66150.8052
2026.02
0.66010.7953
2026.02
0.65890.8031
2026.02
0.65590.7918
2026.02
0.65340.7859
2026.02
0.64980.7269
2026.02
0.64380.7875
2026.02
0.62230.6259
2026.02
0.61750.7871
2026.02
0.61450.6901
2026.02
0.60660.6885
2026.02
0.59730.7627
2026.02
0.59340.6146
2026.02
0.58760.6004
2026.02
0.56620.6333
2026.02
0.56430.5643
2026.02
0.55720.584
2026.02
0.55150.6827
2026.02
0.54480.6113
2026.02
0.53790.6004
2026.02
0.52760.69
2026.02
0.51660.5416
2026.02
0.47550.6025