SOURCE-LINKED INTELLIGENCE

Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Long-text image--text congruence scoring is increasingly important for vision-language systems that must evaluate whether detailed textual descriptions match visual content. However, raw similarity scores from dual-encoder models are difficult to interpret as calibrated congruence measures, especially under the modality gap between image and text embeddings. This paper proposes Congruency Score (CS), a lightweight calibration layer that maps image--text similarity evidence into a bounded score. Using DOCCI and Urban1k, we evaluate four frozen vision-language backbones and show that observed re

Read original source ↗ Open in workspace

recordType

paper

region

Global