SIRA mitigates hallucinations in LVLMs by internally contrasting full visual access against a masked late-layer branch that retains shared context but lacks fine-grained visual evidence.
Detecting and preventing hallucinations in large vision language models.Proceedings of the AAAI Conference on Artificial Intelligence, 38(16): 18135–18143
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
-
Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
SIRA mitigates hallucinations in LVLMs by internally contrasting full visual access against a masked late-layer branch that retains shared context but lacks fine-grained visual evidence.