Saved in:
Bibliographic Details
Main Authors: Pham, Nhi, Schott, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.04077
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless, these models often suffer from hallucinations, e.g., they exhibit inconsistencies between the visual input and the textual output. To address this, we propose H-POPE, a coarse-to-fine-grained benchmark that systematically assesses hallucination in object existence and attributes. Our evaluation shows that models are prone to hallucinations on object existence, and even more so on fine-grained attributes. We further investigate whether these models rely on visual input to formulate the output texts.