List your company
ResearchFormerly WizWand

Hallucination Detection on HalluRAG 1.0 (test)

0.7274F1 ScoreWavelet-high
0.437760.5129550.588150.663345Feb 20, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Wavelet-highModel=Mistral-7B2026.020.72740.836
Fourier-highModel=Mistral-7B2026.020.71520.8128
Lookback-lensModel=Mistral-7B2026.020.71150.7966
LaplacianModel=Mistral-7B2026.020.70010.8098
Attn-entropyModel=Mistral-7B2026.020.68030.7504
Wavelet-highModel=LLaMA-13B2026.020.66840.7809
LaplacianModel=LLaMA-13B2026.020.66590.7624
Fourier-highModel=LLaMA-13B2026.020.66160.7899
Lookback-lensModel=LLaMA-13B2026.020.65940.7929
EigenScoreModel=Mistral-7B2026.020.65810.7924
Fourier-highModel=LLaMA-7B2026.020.64380.7603
Wavelet-highModel=LLaMA-7B2026.020.63840.755
LaplacianModel=LLaMA-7B2026.020.6370.7429
SelfcheckGPTModel=LLaMA-13B2026.020.63370.7216
EigenScoreModel=LLaMA-13B2026.020.63160.6947
Attn-entropyModel=LLaMA-13B2026.020.62840.727
Lookback-lensModel=LLaMA-7B2026.020.62660.7405
RefCheckerModel=Mistral-7B2026.020.61760.6031
RefCheckerModel=LLaMA-13B2026.020.60980.5963
Attn-entropyModel=LLaMA-7B2026.020.6020.6937
RedeepModel=LLaMA-7B2026.020.59120.649
RefCheckerModel=LLaMA-7B2026.020.58190.5722
RedeepModel=LLaMA-13B2026.020.57690.6294
SelfcheckGPTModel=Mistral-7B2026.020.55150.6473
SelfcheckGPTModel=LLaMA-7B2026.020.53880.5963
Attn-varianceModel=Mistral-7B2026.020.53670.6953
EigenScoreModel=LLaMA-7B2026.020.53640.6127
RedeepModel=Mistral-7B2026.020.49870.5646
Attn-varianceModel=LLaMA-13B2026.020.45290.6298
Attn-varianceModel=LLaMA-7B2026.020.44890.5571