# MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs

arXiv: https://arxiv.org/abs/2608.02520 · HTML: https://mlsanity.com/paper/2608.02520/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 3 Aug 2026.

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

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [A Question-Entailment Approach to Question Answering](https://mlsanity.com/paper/1901.08079/) (2019)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care](https://mlsanity.com/paper/2601.16529/) (2026)

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

- [Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit](https://mlsanity.com/paper/2608.29800/) (2026)
- [Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models](https://mlsanity.com/paper/2610.17989/) (2026)
- [Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures](https://mlsanity.com/paper/2610.21270/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used for health-related advice. Existing research measures their safety with static questions rather than pressured patient-facing conversations. We introduce MedPRESS, a multi-turn benchmark for measuring patient-pressure-induced sycophancy in LLMs. MedPRESS contains 600 medically grounded five-turn dialogues across three scenario families: medication and treatment demand, personal health self-care, and symptom triage and care resistance. Each dialogue begins with a health query and escalates through personal experience, social proof, external evidence claims, and direct adversarial challenge. We evaluate 20 LLMs across general, medical-domain, lightweight, large, open-weight, and proprietary families using structured judging and safety-focused metrics. Results show that models frequently shift toward unsafe agreement under repeated patient pressure, with substantial variation across model families, model scale, and prompt type. Anti-sycophancy prompting improves robustness for several models, but does not eliminate unsafe agreement. MedPRESS highlights a critical gap in medical LLM evaluation: safe medical knowledge is not enough unless models can maintain it under conversational pressure.