# Beyond Idealized Patients: Evaluating LLMs under Challenging Patient Behaviors in Medical Consultations

arXiv: https://arxiv.org/abs/2603.29373 · HTML: https://mlsanity.com/paper/2603.29373/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 91 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation](https://mlsanity.com/paper/2010.07497/) (2020)
- [A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets](https://mlsanity.com/paper/2204.08997/) (2022)
- [ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning](https://mlsanity.com/paper/2502.14860/) (2025)
- [MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations](https://mlsanity.com/paper/2410.14204/) (2024)
- [AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning](https://mlsanity.com/paper/2603.21362/) (2026)
- [LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High](https://mlsanity.com/paper/2505.22354/) (2025)
- [Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies](https://mlsanity.com/paper/2406.03827/) (2024)
- [Adversarial Attacks on Large Language Models in Medicine](https://mlsanity.com/paper/2406.12259/) (2024)
- [Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare](https://mlsanity.com/paper/2501.18632/) (2025)
- [The Alignment Waltz: Jointly Training Agents to Collaborate for Safety](https://mlsanity.com/paper/2510.08240/) (2025)
- [Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical Applications](https://mlsanity.com/paper/2507.05517/) (2025)
- [ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning](https://mlsanity.com/paper/2508.19996/) (2025)

## Built on by (most cited first, 3 of 3)

- [MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors](https://mlsanity.com/paper/2604.06846/) (2026)
- [MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models](https://mlsanity.com/paper/2606.24155/) (2026)
- [MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents](https://mlsanity.com/paper/2607.18999/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used for medical consultation and health information support, where safety depends not only on medical knowledge but also on robust responses to unclear, inconsistent, or misleading patient input. However, most existing medical LLM evaluations assume idealized and well-posed patient questions, limiting their realism. We study challenging patient behaviors that commonly arise in real medical consultations and complicate safe clinical reasoning. We define four clinically grounded categories of such behaviors: information contradiction, factual inaccuracy, self-diagnosis, and care resistance. For each behavior, we specify concrete failure criteria that capture unsafe responses. Building on four existing medical dialogue datasets, we introduce CPB-Bench (Challenging Patient Behaviors Benchmark), a bilingual (English and Chinese) benchmark of multi-turn dialogues annotated for these behaviors. We find that although models perform well overall, they exhibit consistent behavior-specific failures, especially when handling contradictory or medically implausible patient information. We further evaluate four intervention strategies and find inconsistent improvements, with some interventions introducing unnecessary corrections.