… their rate of object hallucination. We analyze how captioning model architectures and
learning objectives contribute to object hallucination, explore when hallucination is likely due to …

… the object bias in image captioning models. To reduce object hallucination in image captioning,
… to be treated as ground truth to train image captioning models. By extensive analysis, we …

… LVLMs often suffer from a significant challenge known as hallucination (Rohrbach et al.…
actual objects present in the input image. In this work, we mainly consider object hallucination. …

… For iteration refinement, we hallucinate the generated captions with objects to construct
the pseudo-matched sentences to refine the generator, which incrementally increases the …

… is known as a hallucination [27,38,24] in the literature. Unlike image captioning, there are
two types of hallucination in the case of video captioning: object hallucination occurs when the …

… Work in this paper indicates that features based on object detection model output and
image captioning model output may be a good starting point for designing such a more …

… that enables instruction-tuned LVLMs to reduce fine-grained object hallucination by fine-tuning
them on additional rewritten captions derived from curated high-quality image captions. …

… how human captioning attention can strengthen image captioning. … Recent progress on
image captioning is driven by the development of … Object hallucination in image captioning …

… that image captioning models sometimes hallucinate words … bias image captioning models
from frequently occurring object … generating frequent object words rather than hallucinate them…

… We address the challenges faced in this ield by emphasizing issues such as object
hallucination, missing context, illumination conditions, contextual understanding, and referring …