UniProbe detects hallucinated tokens in frozen LVLMs by jointly modeling attention graphs, image geometry, and response order, and uses this signal to resample bad tokens during generation.
HALP : Detecting Hallucinations in Vision-Language Models without Generating a Single Token
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
UniProbe detects hallucinated tokens in frozen LVLMs by jointly modeling attention graphs, image geometry, and response order, and uses this signal to resample bad tokens during generation.