AIBullisharXiv – CS AI · 10h ago7/10
🧠
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
Researchers identify a fundamental geometric flaw in decoder-based Vision-Language Models where visual embeddings become over-aligned with linguistic patterns, causing systematic hallucinations. The study introduces quantitative methods to characterize this bias and proposes training-free and fine-tuning solutions that reduce hallucinations across multiple benchmarks without computational overhead.