SpanCalib-VLM Multimodal

Token-level hallucination detection: XLM-RoBERTa-Large + SigLIP-2 cross-attention fusion. Best Val Pearson: 0.3688 (Epoch 2/5)

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support