First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models

arXiv:2604.00455 · cs.CV, cs.AI, cs.CL · Submitted 2026-04-01 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2026-04-01

Updated: 2026-04-01

Code: https://github.com/jiwooha20/FLB

Terminology

Sources

Related papers