CHAIRI

CHAIRI is a benchmark dataset used to evaluate hallucination mitigation in large vision-language models.

Papers using CHAIRI (3)

A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model2026LISA: A Layer-wise Integration and Suppression Approach for Hallucination Mitigation in Multimodal Large Language Models2025BIMA: Bijective Maximum Likelihood Learning Approach To Hallucination Prediction And Mitigation In Large Vision-language Models2025