CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
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_ | 1866929573284806656 |
|---|---|
| author | Xia, Peng Chen, Ze Tian, Juanxi Gong, Yangrui Hou, Ruibo Xu, Yue Wu, Zhenbang Fan, Zhiyuan Zhou, Yiyang Zhu, Kangyu Zheng, Wenhao Wang, Zhaoyang Wang, Xiao Zhang, Xuchao Bansal, Chetan Niethammer, Marc Huang, Junzhou Zhu, Hongtu Li, Yun Sun, Jimeng Ge, Zongyuan Li, Gang Zou, James Yao, Huaxiu |
| author_facet | Xia, Peng Chen, Ze Tian, Juanxi Gong, Yangrui Hou, Ruibo Xu, Yue Wu, Zhenbang Fan, Zhiyuan Zhou, Yiyang Zhu, Kangyu Zheng, Wenhao Wang, Zhaoyang Wang, Xiao Zhang, Xuchao Bansal, Chetan Niethammer, Marc Huang, Junzhou Zhu, Hongtu Li, Yun Sun, Jimeng Ge, Zongyuan Li, Gang Zou, James Yao, Huaxiu |
| contents | Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://cares-ai.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06007 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models Xia, Peng Chen, Ze Tian, Juanxi Gong, Yangrui Hou, Ruibo Xu, Yue Wu, Zhenbang Fan, Zhiyuan Zhou, Yiyang Zhu, Kangyu Zheng, Wenhao Wang, Zhaoyang Wang, Xiao Zhang, Xuchao Bansal, Chetan Niethammer, Marc Huang, Junzhou Zhu, Hongtu Li, Yun Sun, Jimeng Ge, Zongyuan Li, Gang Zou, James Yao, Huaxiu Machine Learning Computation and Language Computer Vision and Pattern Recognition Computers and Society Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://cares-ai.github.io/. |
| title | CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models |
| topic | Machine Learning Computation and Language Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2406.06007 |