EnsemHalDet improves VLM hallucination detection by ensembling independent detectors trained on diverse internal states, yielding higher AUC than single-detector baselines across VQA datasets.
InProceedings of the First Workshop on Neural Machine Transla- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors
EnsemHalDet improves VLM hallucination detection by ensembling independent detectors trained on diverse internal states, yielding higher AUC than single-detector baselines across VQA datasets.