SOURCE-LINKED INTELLIGENCE

Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. We connect part of this failure to a measurable property of their representations, feature instability, where mild semantics-preserving perturbations of the input cause large changes in the learned embeddings; hallucination rates rise together with this variability. Existing stability-motivated remedies are explicit, in the sense that they intervene at inference time through latent steering or constrained decoding, and pay for it on every query. We

Read original source ↗ Open in workspace

recordType

paper

region

Global