# MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings

arXiv: https://arxiv.org/abs/2507.07248 · HTML: https://mlsanity.com/paper/2507.07248/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks](https://mlsanity.com/paper/2312.06795/) (2023)
- [Med42-v2: A Suite of Clinical LLMs](https://mlsanity.com/paper/2408.06142/) (2024)
- [Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety](https://mlsanity.com/paper/2503.05021/) (2025)
- [Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle](https://mlsanity.com/paper/2407.13833/) (2024)
- [Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency](https://mlsanity.com/paper/2506.17209/) (2025)
- [MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical Applications](https://mlsanity.com/paper/2409.07314/) (2024)
- [A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment](https://mlsanity.com/paper/2505.10717/) (2025)
- [Does Biomedical Training Lead to Better Medical Performance?](https://mlsanity.com/paper/2404.04067/) (2024)

## Built on by (most cited first, 2 of 2)

- [Measuring Epistemic Resilience of LLMs Under Misleading Medical Context](https://mlsanity.com/paper/2606.12291/) (2026)
- [MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety](https://mlsanity.com/paper/2606.02630/) (2026)

## Abstract (arXiv)

As the performance of large language models (LLMs) continues to advance, their adoption in the medical domain is increasing. However, most existing risk evaluations largely focused on general safety benchmarks. In the medical applications, LLMs may be used by a wide range of users, ranging from general users and patients to clinicians, with diverse levels of expertise and the model's outputs can have a direct impact on human health which raises serious safety concerns. In this paper, we introduce MedRiskEval, a medical risk evaluation benchmark tailored to the medical domain. To fill the gap in previous benchmarks that only focused on the clinician perspective, we introduce a new patient-oriented dataset called PatientSafetyBench containing 466 samples across 5 critical risk categories. Leveraging our new benchmark alongside existing datasets, we evaluate a variety of open- and closed-source LLMs. To the best of our knowledge, this work establishes an initial foundation for safer deployment of LLMs in healthcare.