LLaVA-Bench

Papers using LLaVA-Bench (3)

Self-Consistency as a Free Lunch: Reducing Hallucinations in Vision-Language Models via Self-Reflection2025Smoothguard: Defending Multimodal Large Language Models With Noise Perturbation And Clustering Aggregation2025Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination2024 · 2 cites