Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
OWP is proposed, a training-free framework that shifts hallucination mitigation from output-level manipulation to conflict-conditioned representation rebalancing and adaptively rebalances fused representations by suppressing misleading priors and restoring ignored evidence before decoding.
Zi-Jian Liu, Chaoyou Fu, Yan Yang et al.
· 0 citations