# MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

arXiv: https://arxiv.org/abs/2403.03744 · HTML: https://mlsanity.com/paper/2403.03744/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering](https://mlsanity.com/paper/2203.14371/) (2022)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [Alignment of Language Agents](https://mlsanity.com/paper/2103.14659/) (2021)
- [PMC-LLaMA: Towards Building Open-source Language Models for Medicine](https://mlsanity.com/paper/2304.14454/) (2023)
- [Consequences of Misaligned AI](https://mlsanity.com/paper/2102.03896/) (2021)
- [Towards Conversational Diagnostic AI](https://mlsanity.com/paper/2401.05654/) (2024)

## Built on by (most cited first, 30 of 44)

- [CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs](https://mlsanity.com/paper/2505.11413/) (2025)
- [The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs](https://mlsanity.com/paper/2506.11094/) (2025)
- [Leveraging Large Language Model as Simulated Patients for Clinical Education](https://mlsanity.com/paper/2404.13066/) (2024)
- [Large language models provide unsafe answers to patient-posed medical questions](https://mlsanity.com/paper/2507.18905/) (2025)
- [A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations](https://mlsanity.com/paper/2406.10303/) (2024)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare](https://mlsanity.com/paper/2501.18632/) (2025)
- [MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.20824/) (2025)
- [CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare](https://mlsanity.com/paper/2512.11437/) (2025)
- [From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice](https://mlsanity.com/paper/2410.01812/) (2024)
- [Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety](https://mlsanity.com/paper/2506.12482/) (2025)
- [TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law](https://mlsanity.com/paper/2507.21134/) (2025)
- [When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment](https://mlsanity.com/paper/2506.07452/) (2025)
- [Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education](https://mlsanity.com/paper/2511.14423/) (2025)
- [NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs](https://mlsanity.com/paper/2508.09473/) (2025)
- [ProGuard: Towards Proactive Multimodal Safeguard](https://mlsanity.com/paper/2512.23573/) (2025)
- [Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs](https://mlsanity.com/paper/2510.25441/) (2025)
- [RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models](https://mlsanity.com/paper/2601.03699/) (2026)
- [Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops](https://mlsanity.com/paper/2601.13268/) (2026)
- [Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis](https://mlsanity.com/paper/2604.02359/) (2026)
- [VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation](https://mlsanity.com/paper/2505.13577/) (2025)
- [PAM: Training Policy-Aligned Moderation Filters at Scale](https://mlsanity.com/paper/2505.19766/) (2025)
- [The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy](https://mlsanity.com/paper/2607.11175/) (2026)
- [Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers](https://mlsanity.com/paper/2608.28327/) (2026)
- [Automatic Replication of LLM Mistakes in Medical Conversations](https://mlsanity.com/paper/2512.20983/) (2025)
- [Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control](https://mlsanity.com/paper/2604.26577/) (2026)
- [ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing](https://mlsanity.com/paper/2606.12342/) (2026)
- [NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context](https://mlsanity.com/paper/2505.08734/) (2025)
- [Red Teaming for Generative AI, Report on a Copyright-Focused Exercise Completed in an Academic Medical Center](https://mlsanity.com/paper/2506.22523/) (2025)
- [Text2VLM: Adapting Text-Only Datasets to Evaluate Alignment Training in Visual Language Models](https://mlsanity.com/paper/2507.20704/) (2025)

## Abstract (arXiv)

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for personal and public health, patient safety, and human rights. However, there is little to no understanding of the notion of medical safety in the context of LLMs, let alone how to evaluate and improve it. To address this gap, we first define the notion of medical safety in LLMs based on the Principles of Medical Ethics set forth by the American Medical Association. We then leverage this understanding to introduce MedSafetyBench, the first benchmark dataset designed to measure the medical safety of LLMs. We demonstrate the utility of MedSafetyBench by using it to evaluate and improve the medical safety of LLMs. Our results show that publicly-available medical LLMs do not meet standards of medical safety and that fine-tuning them using MedSafetyBench improves their medical safety while preserving their medical performance. By introducing this new benchmark dataset, our work enables a systematic study of the state of medical safety in LLMs and motivates future work in this area, paving the way to mitigate the safety risks of LLMs in medicine. The benchmark dataset and code are available at https://github.com/AI4LIFE-GROUP/med-safety-bench.