CGC+VTD identifies co-occurring image token clusters as a source of hallucinated objects in discrete-token LVLMs and suppresses clusters' absent-token signals in latent space, cutting hallucination rates across Chameleon, Janus-Pro, and Emu3.
Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
CGC+VTD identifies co-occurring image token clusters as a source of hallucinated objects in discrete-token LVLMs and suppresses clusters' absent-token signals in latent space, cutting hallucination rates across Chameleon, Janus-Pro, and Emu3.