Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors

Excerpt

arXiv:2608.12746v2 Announce Type: replace-cross Abstract: Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with nothing tying an object mention to the image. Most remedies intervene at decoding time, yet under a unified protocol their benefit is confined to short captions; supervised fine-tuning (SFT) on a detail-rich corpus lengthens captions, but over forty percent still name absent objects. This pa