# Overalignment in Frontier LLMs: An Empirical Study of Sycophantic Behaviour in Healthcare

arXiv: https://arxiv.org/abs/2601.18334 · HTML: https://mlsanity.com/paper/2601.18334/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [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)
- [CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models](https://mlsanity.com/paper/2508.17670/) (2025)
- [PARROT: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs](https://mlsanity.com/paper/2511.17220/) (2025)

## Built on by (most cited first, 2 of 2)

- [Why LLMs Give In: Conversational Factors and Reasoning Behind Medical Sycophancy](https://mlsanity.com/paper/2608.01017/) (2026)
- [Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models](https://mlsanity.com/paper/2604.25922/) (2026)

## Abstract (arXiv)

As LLMs are increasingly integrated into clinical workflows, their tendency for sycophancy, prioritizing user agreement over factual accuracy, poses significant risks to patient safety. While existing evaluations often rely on subjective datasets, we introduce a robust framework grounded in medical MCQA with verifiable ground truths. We propose the Adjusted Sycophancy Score, a novel metric that isolates alignment bias by accounting for stochastic model instability, or "confusability". Through an extensive scaling analysis of the Qwen-3 and Llama-3 families, we identify a clear scaling trajectory for resilience. Furthermore, we reveal a counter-intuitive vulnerability in reasoning-optimized "Thinking" models: while they demonstrate high vanilla accuracy, their internal reasoning traces frequently rationalize incorrect user suggestions under authoritative pressure. Our results across frontier models suggest that benchmark performance is not a proxy for clinical reliability, and that simplified reasoning structures may offer superior robustness against expert-driven sycophancy.