List your company

Hallucination Detection on SQuAD

0.721AUCsLSC
0.251960.373730.49550.61727Jan 7, 2026

Evaluation results

MethodLinks
LSCModel=Qwen-0.5B2026.010.721—0.7420.411
EigenScoreModel=Qwen-0.5B2026.010.698—0.7120.366
Lexical SimilarityModel=Qwen-0.5B2026.010.67—0.6980.317
AGSERModel=Qwen-0.5B2026.010.631—0.6470.22
LN-EntropyModel=Qwen-0.5B2026.010.589—0.6090.155
PerplexityModel=Qwen-0.5B2026.010.538—0.5690.151
EigenScoreModel=Qwen-32B2026.010.491—0.5120.076
LSCModel=Qwen-32B2026.010.483—0.5170.081
EnergyModel=Qwen-0.5B2026.010.478—0.493-0.028
Lexical SimilarityModel=Qwen-32B2026.010.471—0.5040.047
LN-EntropyModel=Qwen-32B2026.010.448—0.4970.022
AGSERModel=Qwen-32B2026.010.425—0.4920.027
PerplexityModel=Qwen-32B2026.010.345—0.443-0.063
EnergyModel=Qwen-32B2026.010.27—0.342-0.17
ICR ProbeModel=Qwen2.5-14B2025.07—0.7632——
ICR ProbeModel=Qwen2.5-3B2025.07—0.7784——
SAPLMAModel=Qwen2.5-14B2025.07—0.6984——
SAPLMAModel=Qwen2.5-3B2025.07—0.6915——
SEPModel=Qwen2.5-14B2025.07—0.6653——
SEPModel=Qwen2.5-3B2025.07—0.656——