Haiyang Xu

Evaluation and Analysis of Hallucination in Large Vision-Language Models

2023 · arXiv (Cornell University)

Large Vision-Language Models (LVLMs) have recently achieved remarkable success. However, LVLMs are still plagued by the hallucination problem, which limits the practicality in many scenarios. Hallucination refers to the information of LVLMs' responses that does …

Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models

2024 · arXiv (Cornell University)

Large Vision Language Models exhibit remarkable capabilities but struggle with hallucinations inconsistencies between images and their descriptions. Previous hallucination evaluation studies on LVLMs have identified hallucinations in terms of objects, attributes, and relations but overlooked …