Omnimodal LLMs encode premise-perception mismatches in hidden states yet almost never reject false textual claims, exposing a representation-action gap that is modality-asymmetric and prompt-resistant.
Fork-merge decoding: Enhancing multimodal understanding in audio-visual large language models.arXiv preprint arXiv:2505.20873, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AVLLMs store integrated audio-visual information mainly in a distinct subset of sink tokens called cross-modal sink tokens, which can be leveraged for training-free hallucination mitigation.
citing papers explorer
-
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
Omnimodal LLMs encode premise-perception mismatches in hidden states yet almost never reject false textual claims, exposing a representation-action gap that is modality-asymmetric and prompt-resistant.
-
Probing Cross-modal Information Hubs in Audio-Visual LLMs
AVLLMs store integrated audio-visual information mainly in a distinct subset of sink tokens called cross-modal sink tokens, which can be leveraged for training-free hallucination mitigation.