SOURCE-LINKED INTELLIGENCE

SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models

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

Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-calibrated confidence scores. Fine-tuned generative VLMs excel at identifying hallucinated text spans but suffer from overconfidence and high inference latency. Discriminative sequence taggers offer deterministic speed and superior calibration but exhibit conservative span recall. We present SpanCalib-VLM, a hybrid dual-system for the SHROOM-Visions Shared Task that combines a multimodal sequence tagger, consisting of XLM-RoBERTa-Large fused with a SigLIP vision encoder via cross-

Read original source ↗ Open in workspace

recordType

paper

region

Global