Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Soroosh Tayebi Arasteh

Soroosh Tayebi Arasteh

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2AI×2ML×2Info Retrieval×1Vision×1

Frequent co-authors

Mahshad Lotfinia1×
Sven Nebelung1×
Daniel Truhn1×

Research Timeline

2026
Cross-modal linkage risk in clinical vision-language models

The paper demonstrates that clinical vision-language models (VLMs) pose a significant privacy risk by allowing de-identified images to be re-linked to original reports, and proposes a targeted differential privacy (DP) fine-tuning method to mitigate this risk while preserving clinical utility.

The strength of clinical evidence is recoverable from language model representations but not from their stated grades

This paper evaluates the ability of large language models to recover and express evidence grades from clinical claims, finding that while they can recover the grades, they do not consistently express them.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.IREmpiricalRecentJun 27, 2026

The strength of clinical evidence is recoverable from language model representations but not from their stated grades

Soroosh Tayebi Arasteh

This paper evaluates the ability of large language models to recover and express evidence grades from clinical claims, finding that while they can recover the grades, they do not consistently express…

View →
cs.CVcs.AIcs.CLRecent
Jun 1, 2026

Cross-modal linkage risk in clinical vision-language models

Soroosh Tayebi Arasteh, Mahshad Lotfinia, Sven Nebelung, Daniel Truhn

The paper demonstrates that clinical vision-language models (VLMs) pose a significant privacy risk by allowing de-identified images to be re-linked to original reports, and proposes a targeted differe…

View →