List your company

Hallucination Detection on WNMCQ1

87.5PRRFunction Vector
57.3465.177380.83Apr 28, 2026

Evaluation results

MethodLinks
Function VectorModel=LLaMA2-13B2026.0487.5
Self-FVModel=LLaMA2-7B2026.0486.6
Function VectorModel=LLaMA2-7B2026.0486.5
Self-FVModel=LLaMA2-13B2026.0486.2
Semantic EntropyModel=LLaMA2-13B2026.0485.9
Total EntropyModel=LLaMA2-13B2026.0484.1
Total EntropyModel=LLaMA2-7B2026.0482.8
Semantic EntropyModel=LLaMA2-7B2026.0481.5
UQ_ICLModel=LLaMA2-13B2026.0473
UQ_ICLModel=LLaMA2-7B2026.0458.5