Our new X account is live! Follow @wizwand_team for updates

Hallucination Detection on TriviaQA

0.95AUROC

SAPLMA

Updated 3d ago

Evaluation Results

Method
SAPLMA 2025.12	0.95	-	-	-	-	-	-	-
DRIFT 2026.01	0.9395	-	-	-	-	-	-	-
Latent Debate Detector 2025.12	0.93	-	-	-	-	-	-	-
ARS (Probing) 2026.01	0.9162	-	-	-	-	-	-	-
G-Detector 2026.01	0.9052	-	-	-	-	-	-	-
TSV 2026.01	0.8967	-	-	-	-	-	-	-
HaluNet 2025.12	0.893	-	-	-	0.977	0.601	0.984	-
P(True) 2025.12	0.891	-	-	-	0.937	0.727	0.961	-
DRIFT 2026.01	0.8896	-	-	-	-	-	-	-
ARS (CCS) 2026.01	0.8886	-	-	-	-	-	-	-
DRIFT 2026.01	0.888	-	-	-	-	-	-	-
ARS (CCS) 2026.01	0.8854	-	-	-	-	-	-	-
ARS (Probing) 2026.01	0.8745	-	-	-	-	-	-	-
DRIFT 2026.01	0.8731	-	-	-	-	-	-	-
SpikeScore 2026.01	0.8697	-	-	-	-	-	-	-
RACE 2026.01	0.8657	-	-	-	-	-	-	-
HaloScope 2026.01	0.8654	-	-	-	-	-	-	-
TSV 2026.01	0.8573	-	-	-	-	-	-	-
HaluNet 2025.12	0.856	-	-	-	0.948	0.665	0.96	-
HaloScope 2026.01	0.8548	-	-	-	-	-	-	-
Logistic 2025.12	0.848	-	-	-	0.93	0.577	0.955	-
PR 2026.01	0.8466	-	-	-	-	-	-	-
PR 2026.01	0.8436	-	-	-	-	-	-	-
PR 2026.01	0.8436	-	-	-	-	-	-	-
PR 2026.01	0.8422	-	-	-	-	-	-	-
PR 2026.01	0.8421	-	-	-	-	-	-	-
SpikeScore 2026.01	0.8413	-	-	-	-	-	-	-
MoP 2026.01	0.8412	-	-	-	-	-	-	-
MoP 2026.01	0.8403	-	-	-	-	-	-	-
DRIFT 2026.01	0.8393	-	-	-	-	-	-	-
MoP 2026.01	0.8357	-	-	-	-	-	-	-
MoP 2026.01	0.8357	-	-	-	-	-	-	-
PR 2026.01	0.8313	-	-	-	-	-	-	-
PR 2026.01	0.8313	-	-	-	-	-	-	-
SEU 2025.12	0.827	-	-	-	0.03	0.457	0.023	-
MoP-VanillaExperts 2026.01	0.8247	-	-	-	-	-	-	-
DRIFT 2026.01	0.821	-	-	-	-	-	-	-
P(True) 2025.12	0.819	-	-	-	0.962	0.415	0.978	-
Probing Baseline 2026.01	0.8174	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.8174	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.8159	-	-	-	-	-	-	-
Semantic Entropy 2026.01	0.8123	-	-	-	-	-	-	-
MoP 2026.01	0.8118	-	-	-	-	-	-	-
MoP 2026.01	0.8118	-	-	-	-	-	-	-
MoP-VanillaExperts 2026.01	0.8093	-	-	-	-	-	-	-
MoP-VanillaExperts 2026.01	0.8093	-	-	-	-	-	-	-
PR 2026.01	0.8066	-	-	-	-	-	-	-
MoP 2026.01	0.8007	-	-	-	-	-	-	-
MoP-VanillaExperts 2026.01	0.7951	-	-	-	-	-	-	-
SpikeScore 2026.01	0.7947	-	-	-	-	-	-	-
Logistic 2025.12	0.794	-	-	-	0.926	0.558	0.937	-
MoP-VanillaExperts 2026.01	0.7873	-	-	-	-	-	-	-
MoP-VanillaExperts 2026.01	0.7873	-	-	-	-	-	-	-
MoP 2026.01	0.7872	-	-	-	-	-	-	-
MoP-VanillaExperts 2026.01	0.7863	-	-	-	-	-	-	-
Semantic Entropy 2026.01	0.7848	-	-	-	-	-	-	-
ICR Probe 2025.07	0.7846	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.7843	-	-	-	-	-	-	-
ICR Probe 2026.01	0.7841	-	-	-	-	-	-	-
EmbVar 2025.12	0.781	-	-	-	0.945	0.378	0.973	-
SelfCheckGPT 2025.12	0.779	-	-	-	0.934	0.356	0.978	-
MoP-VanillaExperts 2026.01	0.7768	-	-	-	-	-	-	-
SAPLMA 2025.07	0.7759	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.7758	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.7758	-	-	-	-	-	-	-
HaloScope 2026.01	0.774	-	-	-	-	-	-	-
SelfCheckGPT 2025.12	0.774	-	-	-	0.884	0.588	0.907	-
SpikeScore 2026.01	0.7737	-	-	-	-	-	-	-
Logits-min 2026.01	0.7733	-	-	-	-	-	-	-
Logits-min 2026.01	0.7733	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.7717	-	-	-	-	-	-	-
SpikeScore 2026.01	0.7689	-	-	-	-	-	-	-
ICR Probe 2026.01	0.7682	-	-	-	-	-	-	-
Probing Baseline 2026.01	0.7661	-	-	-	-	-	-	-
SE 2025.12	0.766	-	-	-	0.948	0.409	0.967	-
Logits-min 2026.01	0.7656	-	-	-	-	-	-	-
SpikeScore 2026.01	0.7654	-	-	-	-	-	-	-
HaloScope 2026.01	0.7652	-	-	-	-	-	-	-
ICR Probe 2025.07	0.7631	-	-	-	-	-	-	-
SEU 2025.12	0.763	-	-	-	0.107	0.536	0.087	-
Semantic Entropy 2026.01	0.7608	-	-	-	-	-	-	-
ICR Probe 2026.01	0.7532	-	-	-	-	-	-	-
SAPLMA 2025.07	0.7523	-	-	-	-	-	-	-
SE 2025.12	0.75	-	-	-	0.88	0.542	0.904	-
ICR Probe 2026.01	0.7495	-	-	-	-	-	-	-
ICR Probe 2026.01	0.7464	-	-	-	-	-	-	-
EmbVar 2025.12	0.744	-	-	-	0.863	0.49	0.912	-
SpikeScore 2026.01	0.741	-	-	-	-	-	-	-
TDGNet 2026.02	0.74	-	-	-	-	-	-	-
ICR Probe 2026.01	0.7337	-	-	-	-	-	-	-
ICR Probe 2026.01	0.7317	-	-	-	-	-	-	-
SpikeScore 2026.01	0.7316	-	-	-	-	-	-	-
ICR Probe 2026.01	0.731	-	-	-	-	-	-	-
MoP-RandomGate 2026.01	0.7238	-	-	-	-	-	-	-
PE 2025.12	0.723	-	-	-	0.913	0.394	0.952	-
TDGNet 2026.02	0.72	-	-	-	-	-	-	-
TDGNet 2026.02	0.72	-	-	-	-	-	-	-
PE 2025.12	0.719	-	-	-	0.9	0.361	0.92	-
SEP 2025.07	0.7103	-	-	-	-	-	-	-
Lexical Similarity 2026.01	0.7102	-	-	-	-	-	-	-

Showing 100 of 307 rows