A multilingual hallucination detector that flags words where a language-specialized model's perplexity diverges from the rest, achieving IoU around 0.3.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ask a Local: Detecting Hallucinations With Specialized Model Divergence
A multilingual hallucination detector that flags words where a language-specialized model's perplexity diverges from the rest, achieving IoU around 0.3.