# When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure

arXiv: https://arxiv.org/abs/2605.23932 · HTML: https://mlsanity.com/paper/2605.23932/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (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)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [Inspecting and Editing Knowledge Representations in Language Models](https://mlsanity.com/paper/2304.00740/) (2023)
- [The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation](https://mlsanity.com/paper/2312.09085/) (2023)
- [Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions](https://mlsanity.com/paper/2402.18060/) (2024)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)
- [Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters](https://mlsanity.com/paper/2410.24190/) (2024)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate](https://mlsanity.com/paper/2509.23055/) (2025)
- [A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare](https://mlsanity.com/paper/2502.15871/) (2025)
- [Teaching Models to Balance Resisting and Accepting Persuasion](https://mlsanity.com/paper/2410.14596/) (2024)
- [Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA](https://mlsanity.com/paper/2508.13743/) (2025)
- [Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD](https://mlsanity.com/paper/2508.17450/) (2025)
- [Enhancing Cross-task Transfer of Large Language Models via Activation Steering](https://mlsanity.com/paper/2507.13236/) (2025)

## Built on by (most cited first, 6 of 6)

- [AI Can Be Easily Persuaded in Clinical Decision Making](https://mlsanity.com/paper/2608.29453/) (2026)
- [Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit](https://mlsanity.com/paper/2608.29800/) (2026)
- [Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models](https://mlsanity.com/paper/2609.22161/) (2026)
- ["You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused](https://mlsanity.com/paper/2609.32616/) (2026)
- [Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding](https://mlsanity.com/paper/2610.08840/) (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)

## Abstract (arXiv)

Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis under escalating pressure. We propose textbftextscMed-Stress, a targeted stress test framework that evaluates belief stability under escalating pressure. Across nine frontier large language models (LLMs), we find a clear dissociation between medical knowledge and robustness: high initial diagnostic capability does not imply high belief stability, yielding large knowledge-robustness gaps for several LLMs. To mitigate this failure mode, we propose a lightweight inference-time defense, textbftextttRBED (Role-Based Epistemic Defense), and textbftextttR-FT (Resilience-oriented Fine-Tuning), a training-time approach that internalizes evidence-based resistance to pressure. Experiments show that textbftextttR-FT nearly eliminates belief change and substantially improves robustness.