List your company

Hallucination Detection on 80 Experiments Aggregated (test)

6.16Average RankKLE (heat)
6.05046.79027.538.2698May 27, 2026

Evaluation results

MethodLinks
KLE (heat)Multi-sample?=Yes2026.056.16
KLEMulti-sample?=Yes2026.056.16
CES (unsup.)Multi-sample?=No2026.056.29
KLE (full)Multi-sample?=Yes2026.056.65
Embed. Regr.Multi-sample?=Yes2026.056.92
CES (sup.)Multi-sample?=No2026.057.03
LN EntropyMulti-sample?=No2026.058.2
PerplexityMulti-sample?=No2026.058.2
Discrete SEMulti-sample?=Yes2026.058.61
LNE (bench)Multi-sample?=No2026.058.9