Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs

A team of researchers posted arXiv paper 2610.27103v1 introducing Omni-Woodpecker (OWP), a training-free framework that reduces cross-modal hallucinations in Omni LLMs by rebalancing fused representations before decoding rather than correcting outputs. Using Qwen2.5-Omni-7B as the backbone, OWP improved scores by 12.9 points on CMM and 8.6 points on AVHBench, with gains of 0.67-2.25 points across four general OLLM reasoning benchmarks, and it generalized to VideoLLaMA2-AV with gains of 4.6 and 3.9 points on the same benchmarks. The code is publicly available on GitHub.

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 output-level manipulation to conflict-conditioned representation rebalancing. Specifically, OWP first identifies cross-modal conflicts from complementary modality-specific views. It then employs orthogonal decomposition to separate grounding evidence from competing priors within the hidden states. Finally, OWP adaptively rebalances fused representations by suppressing misleading priors and restoring ignored evidence before decoding. Extensive experiments demonstrate the effectiveness and strong cross-architecture generalization of OWP. Using Qwen2.5-Omni-7B as the backbone, OWP improves performance by 12.9 and 8.6 points on CMM and AVHBench, respectively, while consistently achieving gains of 0.67-2.25 points across four general OLLM reasoning benchmarks. Furthermore, OWP generalizes effectively to VideoLLaMA2-AV, improving performance by 4.6 and 3.9 points on the same benchmarks. Code is publicly available at https://github.com/ZiiJianLiu/Omni-Woodpecker