SOURCE-LINKED INTELLIGENCE
Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models
Multimodal large language models generate natural-language responses from visual inputs, yet may mention objects absent from an image. In medication assistance, accessible perception, and environmental decision-making, such hallucinations can create real-world safety risks. We propose Semantic-Spatial Agreement Verification (SSAV), a training-free method for verifying object claims. A visually grounded claim should remain stable across semantically equivalent queries and repeatedly localize to the same image region. SSAV aggregates multiple prompts to estimate semantic support and reduce sensi
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-15T14:48:48.000Z
First collected: 2026-09-20T08:40:59.508Z. This is not the publication date.