P\textsuperscript{2}-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization

Ruipeng Zhang, Zhihao Li, Haozhang Yuan, C. L. Philip Chen, Tong Zhang

Jun 3, 2026 at 04:00

11 Views

0 Comments

arXiv:2606.03376v1 Announce Type: cross Abstract: Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans, thereby addressing the hallucination issue. Despite its success, this paradigm...

Read the full article at the source.

Read Original Article

Was this helpful?