amanuelbyte's picture
Upload README.md with huggingface_hub
2b88199 verified
|
Raw
History Blame Contribute Delete
273 Bytes
metadata
tags:
  - hallucination-detection
  - xlm-roberta
  - siglip
  - span-detection
  - multimodal
language: en
license: mit

SpanCalib-VLM Multimodal

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