One Year Later...The Harms Persist, But So Do We!

arXiv cs.CL Papers

Summary

This study evaluates six proprietary LLMs across 16 DSM-5 conditions using adversarial attacks, finding that safety safeguards are only reliable for suicide and self-harm, with failure rates up to 100% for other conditions like eating disorders and substance use disorder.

arXiv:2606.23884v1 Announce Type: new Abstract: General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate and inconsistent across clinical conditions. This study evaluates six proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework. Results show that safeguards hold reliably only for suicide and self-harm, while conditions such as eating disorders, substance use disorder, and major depressive disorder exhibit failure rates of up to 100%. We argue that ethical design and deployment of these LLMs demand clearly defined harm categories across clinical conditions and implementation of safeguards accordingly. Until such safeguards are in place, these models pose significant risks to vulnerable populations, making their growing integration into educational settings a particularly concerning.
Original Article
View Cached Full Text

Cached at: 06/24/26, 07:43 AM

# One Year Later...The Harms Persist, But So Do We!
Source: [https://arxiv.org/abs/2606.23884](https://arxiv.org/abs/2606.23884)
[View PDF](https://arxiv.org/pdf/2606.23884)

> Abstract:General\-purpose large language models \(LLMs\) are increasingly used for mental health\-related conversations, yet safety safeguards remain inadequate and inconsistent across clinical conditions\. This study evaluates six proprietary LLMs across 16 DSM\-5 conditions using four adversarial attack variants, introducing an eight\-dimension harm taxonomy and a multi\-dimensional evaluation framework\. Results show that safeguards hold reliably only for suicide and self\-harm, while conditions such as eating disorders, substance use disorder, and major depressive disorder exhibit failure rates of up to 100%\. We argue that ethical design and deployment of these LLMs demand clearly defined harm categories across clinical conditions and implementation of safeguards accordingly\. Until such safeguards are in place, these models pose significant risks to vulnerable populations, making their growing integration into educational settings a particularly concerning\.

## Submission history

From: Annika Marie Schoene \[[view email](https://arxiv.org/show-email/397736a3/2606.23884)\] **\[v1\]**Mon, 22 Jun 2026 19:30:14 UTC \(460 KB\)

Similar Articles

Using Fine-Tuned LLMs to Identify Indicators of Vulnerability in UK Police Incident Logs

arXiv cs.CL

This paper explores using fine-tuned LLMs to identify indicators of vulnerability (mental ill health, substance misuse, alcohol dependence, homelessness) in UK police incident logs, finding that while LLMs can produce meaningful prevalence estimates, they require careful methodological support and are not reliable for individual-level decisions.