MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929408053346304 |
|---|---|
| author | Gu, Zishan Yin, Changchang Liu, Fenglin Zhang, Ping |
| author_facet | Gu, Zishan Yin, Changchang Liu, Fenglin Zhang, Ping |
| contents | Large Vision Language Models (LVLMs) have recently achieved superior performance in various tasks on natural image and text data, which inspires a large amount of studies for LVLMs fine-tuning and training. Despite their advancements, there has been scant research on the robustness of these models against hallucination when fine-tuned on smaller datasets. In this study, we introduce a new benchmark dataset, the Medical Visual Hallucination Test (MedVH), to evaluate the hallucination of domain-specific LVLMs. MedVH comprises five tasks to evaluate hallucinations in LVLMs within the medical context, which includes tasks for comprehensive understanding of textual and visual input, as well as long textual response generation. Our extensive experiments with both general and medical LVLMs reveal that, although medical LVLMs demonstrate promising performance on standard medical tasks, they are particularly susceptible to hallucinations, often more so than the general models, raising significant concerns about the reliability of these domain-specific models. For medical LVLMs to be truly valuable in real-world applications, they must not only accurately integrate medical knowledge but also maintain robust reasoning abilities to prevent hallucination. Our work paves the way for future evaluations of these studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02730 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context Gu, Zishan Yin, Changchang Liu, Fenglin Zhang, Ping Computer Vision and Pattern Recognition Artificial Intelligence Large Vision Language Models (LVLMs) have recently achieved superior performance in various tasks on natural image and text data, which inspires a large amount of studies for LVLMs fine-tuning and training. Despite their advancements, there has been scant research on the robustness of these models against hallucination when fine-tuned on smaller datasets. In this study, we introduce a new benchmark dataset, the Medical Visual Hallucination Test (MedVH), to evaluate the hallucination of domain-specific LVLMs. MedVH comprises five tasks to evaluate hallucinations in LVLMs within the medical context, which includes tasks for comprehensive understanding of textual and visual input, as well as long textual response generation. Our extensive experiments with both general and medical LVLMs reveal that, although medical LVLMs demonstrate promising performance on standard medical tasks, they are particularly susceptible to hallucinations, often more so than the general models, raising significant concerns about the reliability of these domain-specific models. For medical LVLMs to be truly valuable in real-world applications, they must not only accurately integrate medical knowledge but also maintain robust reasoning abilities to prevent hallucination. Our work paves the way for future evaluations of these studies. |
| title | MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.02730 |