AINeutralarXiv – CS AI · 6h ago6/10
🧠
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
Researchers propose MGAP, a training-free decoding method that reduces hallucinations in multimodal large language models (MLLMs) by selectively suppressing language priors while preserving semantic structure. Unlike previous approaches that blindly penalize language biases, MGAP uses geometry-aware subspace projection to distinguish between helpful and harmful language priors, achieving improved hallucination suppression without degrading model coherence.