Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.08030 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912475699478528 |
|---|---|
| author | Sharma, Sonali Alaa, Ahmed M. Daneshjou, Roxana |
| author_facet | Sharma, Sonali Alaa, Ahmed M. Daneshjou, Roxana |
| contents | Generative AI models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used to interpret medical images and answer clinical questions. Their responses often include inaccuracies; therefore, safety measures like medical disclaimers are critical to remind users that AI outputs are not professionally vetted or a substitute for medical advice. This study evaluated the presence of disclaimers in LLM and VLM outputs across model generations from 2022 to 2025. Using 500 mammograms, 500 chest X-rays, 500 dermatology images, and 500 medical questions, outputs were screened for disclaimer phrases. Medical disclaimer presence in LLM and VLM outputs dropped from 26.3% in 2022 to 0.97% in 2025, and from 19.6% in 2023 to 1.05% in 2025, respectively. By 2025, the majority of models displayed no disclaimers. As public models become more capable and authoritative, disclaimers must be implemented as a safeguard adapting to the clinical context of each output. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08030 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Systematic Analysis of Declining Medical Safety Messaging in Generative AI Models Sharma, Sonali Alaa, Ahmed M. Daneshjou, Roxana Computation and Language Computational Engineering, Finance, and Science Human-Computer Interaction Generative AI models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used to interpret medical images and answer clinical questions. Their responses often include inaccuracies; therefore, safety measures like medical disclaimers are critical to remind users that AI outputs are not professionally vetted or a substitute for medical advice. This study evaluated the presence of disclaimers in LLM and VLM outputs across model generations from 2022 to 2025. Using 500 mammograms, 500 chest X-rays, 500 dermatology images, and 500 medical questions, outputs were screened for disclaimer phrases. Medical disclaimer presence in LLM and VLM outputs dropped from 26.3% in 2022 to 0.97% in 2025, and from 19.6% in 2023 to 1.05% in 2025, respectively. By 2025, the majority of models displayed no disclaimers. As public models become more capable and authoritative, disclaimers must be implemented as a safeguard adapting to the clinical context of each output. |
| title | A Systematic Analysis of Declining Medical Safety Messaging in Generative AI Models |
| topic | Computation and Language Computational Engineering, Finance, and Science Human-Computer Interaction |
| url | https://arxiv.org/abs/2507.08030 |