Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
Large language models (LLMs) are rapidly transitioning into medical clinical use, yet their reliability under realistic, multi-turn interactions remains poorly understood. Existing evaluation frameworks typically assess single-turn question answering under idealized conditions, overlooking the complexities of medical consultations where conflicting input, misleading context, and authority influence are common. We introduce MedQA-Followup, a framework for systematically evaluating multi-turn robustness in medical question answering. Our approach distinguishes between shallow robustness (resisting misleading initial context) and deep robustness (maintaining accuracy when answers are challenged across turns), while also introducing an indirect-direct axis that separates contextual framing (indirect) from explicit suggestion (direct). Using controlled interventions on the MedQA dataset, we evaluate five state-of-the-art LLMs and find that while models perform reasonably well under shallow perturbations, they exhibit severe vulnerabilities in multi-turn settings, with accuracy dropping from 91.2% to as low as 13.5% for Claude Sonnet 4. Counterintuitively, indirect, context-based interventions are often more harmful than direct suggestions, yielding larger accuracy drops across models and exposing a significant vulnerability for clinical deployment. Further compounding analyses reveal model differences, with some showing additional performance drops under repeated interventions while others partially recovering or even improving. These findings highlight multi-turn robustness as a critical but underexplored dimension for safe and reliable deployment of medical LLMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #1 | Question Answering | MedQA | MedQA-Followup | Accuracy: 91.2 |
Similar Papers 제목 키워드 기반
MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
Recent advancements in Large Language Models (LLMs) have significantly enhanced their code generation capabilities. However, their robustness against adversarial misuse, particularly through multi-turn malicious coding p…
Code GenerationTransient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack te…
Adversarial RobustnessEvaluating False Alarm and Missing Attacks in CAN IDS
Modern vehicles rely on electronic control units (ECUs) interconnected through the Controller Area Network (CAN), making in-vehicle communication a critical security concern. Machine learning (ML)-based intrusion detecti…
Adversarial RobustnessIntrusion DetectionSafety Alignment Should Be Made More Than Just a Few Tokens Deep
The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to …
Safety AlignmentIs Length Really A Liability? An Evaluation of Multi-turn LLM Conversations using BoolQ
Single-prompt evaluations dominate current LLM benchmarking, yet they fail to capture the conversational dynamics where real-world harm occurs. In this study, we examined whether conversation length affects response vera…