SOURCE-LINKED INTELLIGENCE

Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-occurrence statistics. We challenge this view by presenting quantitative evidence for a complementary, under-explored cause: visual-origin hallucination, where hallucinations arise from incorrect visual feature extraction and misalignment between image and text embeddings. Through cosine similarity analysis and Smooth Grad-CAM entropy measurements, we show that hallucinated samples exhibit systematically lower image-te

Read original source ↗ Open in workspace

recordType

paper

region

Global