Book
Open access
Nov 2026
SADI: Spatial-Aware Dynamic Intervention for Mitigating Hallucinations in LVLMs
Large Vision-Language Models (LVLMs) persistently suffer from object hallucinations, generating plausible yet factually incorrect outputs that fabricate objects non-existent in the visual input. Existing mitigation methods typically fall into three paradigms: fine-tuning with targeted data, which incurs prohibitive com...
Yuan-Zhi Xu, Qian Gao, Jun Fan et al.
· 0 citations