List your company

Hallucination Detection on GSM8k (PRR)

0.571PRRSelf-FV
-0.064440.100530.26550.43047May 26, 2025Jul 21, 2025Sep 15, 2025Nov 10, 2025Jan 5, 2026Mar 2, 2026Apr 28, 2026

Evaluation results

MethodLinks
Self-FVModel=LLaMA2-7B2026.040.571
Function VectorModel=LLaMA2-7B2026.040.518
UQ_ICLModel=LLaMA2-13B2026.040.337
TADBackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.323
RAUQBackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.323
MINDBackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.316
SheepsBackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.31
SATRMD+MSPBackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.307
Semantic EntropyModel=LLaMA2-13B2026.040.293
Semantic EntropyModel=LLaMA2-7B2026.040.277
Self-FVModel=LLaMA2-13B2026.040.27
Function VectorModel=LLaMA2-13B2026.040.261
LookBackLensBackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.189
Total EntropyModel=LLaMA2-13B2026.040.179
UQ_ICLModel=LLaMA2-7B2026.040.159
SAPLMABackbone=Llama-3.1 8B, Setup=out-of-domain2025.050.152
Total EntropyModel=LLaMA2-7B2026.040.107
FactoscopeBackbone=Llama-3.1 8B, Setup=out-of-domain2025.05-0.04