# Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous

arXiv: https://arxiv.org/abs/2509.08833 · HTML: https://mlsanity.com/paper/2509.08833/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2025.

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

- [Position: Universal Aesthetic Alignment Narrows Artistic Expression](https://mlsanity.com/paper/2512.11883/) (2025)
- [MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts](https://mlsanity.com/paper/2607.18673/) (2026)
- [Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models](https://mlsanity.com/paper/2609.12277/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are usually aligned with "human values/preferences" to prevent harmful output. Discussions around the alignment of Large Language Models (LLMs) generally focus on preventing harmful outputs. However, in this paper, we argue that in health-related queries, over-alignment-leading to overly cautious responses-can itself be harmful, especially for people with anxiety and obsessive-compulsive disorder (OCD). This is not only unethical but also dangerous to the user, both mentally and physically. We also showed qualitative results that some LLMs exhibit varying degrees of alignment. Finally, we call for the development of LLMs with stronger reasoning capabilities that provide more tailored and nuanced responses to health queries. Warning: This paper contains materials that could trigger health anxiety or OCD. Dataset and full results can be found in https://github.com/weathon/over-alignment.