Omni-Woodpecker framework reduces cross-modal hallucination
The story so far
The Omni-Woodpecker framework reduces cross-modal hallucinations in full-modal large models by identifying modal conflicts and rebalancing hidden representations without training. The framework improved Qwen2.5-Omni-7B by 12.9 and 8.6 points on CMM and AVHBench, and continuously improved by 0.67-2.25 points on four general OLLM inference benchmarks. The code is open-sourced.
AI-written from the reports · Updated 24 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersOmni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
Omni-Woodpecker is a training-free framework that reduces cross-modal hallucinations in multimodal large models by identifying modal conflicts and rebalancing hidden representations, improving Qwen2.5-Omni-7B by 12.9 and 8.6 points on CMM and AVHBench, respectively, and consistently improving by 0.67-2.25 points on four general OLLM reasoning benchmarks, with the code open-sourced.