The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are detectable. This work studies that heterogeneity across four language models and three factual question answering datasets. Partitioning hallucinations by answer agreem...
Pranav Darshan, A. Pranav, T. SravanKarthick et al.
· 0 citations