一年后...伤害持续，但我们仍在！
One Year Later...The Harms Persist, But So Do We!
AI总结：
研究评估六种商用大语言模型在16种DSM-5条件下的安全性，发现除自杀和自伤外，其他精神障碍（如进食障碍、物质使用障碍、重度抑郁障碍）的防护失败率高达100%，呼吁按临床条件定义伤害类别并实施防护。
摘要：
通用大语言模型（LLM）越来越多地用于心理健康相关对话，但其安全防护措施在不同临床条件下仍然不足且不一致。本研究使用四种对抗性攻击变体，评估了六种商用LLM在16种DSM-5条件下的表现，引入了一个八维伤害分类法和一个多维评估框架。结果表明，防护仅在自杀和自伤条件下可靠，而进食障碍、物质使用障碍和重度抑郁障碍等条件的失败率高达100%。我们认为，这些LLM的道德设计和部署需要明确界定跨临床条件的伤害类别，并相应实施防护措施。在实施此类防护措施之前，这些模型对弱势群体构成重大风险，使其在教育环境中的日益整合尤其令人担忧。
英文摘要：
General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety guardrails remain inadequate and inconsistent across clinical conditions. This study evaluates eight 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 publicly available settings (e.g., schools, search engines, and consumer chatbots) are particularly concerning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
