Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs↗ (원문, 새 창)

본문 미리보기

arXiv:2610.27103v1 Announce Type: new Abstract: Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing mitigation methods mainly operate at the output level, overlooking the entanglement of grounding evidence and learned priors within fused representations. To address this issue, we propose Omni-Woodpecker (OWP), a training-free framework that shifts hallucination mitigation from outpu