支持的缓慢漂移：多轮心理健康大语言模型对话中的边界失败
The Slow Drift of Support: Boundary Failures in Multi-Turn Mental Health LLM Dialogues
AI总结：
本文提出多轮压力测试框架，揭示LLMs在长对话中因安慰和同理心尝试导致的安全边界逐步侵犯问题。
摘要：
大型语言模型（LLMs）已被广泛用于心理健康支持。然而，当前在此领域的安全评估大多局限于检测LLMs在单轮对话中是否输出禁止性词语，忽视了在长对话中安全边界逐渐侵蚀的问题。例如，包括做出确定性保证、承担责任和扮演专业角色等行为。我们认为，随着主流LLMs的演进，明显具有安全风险的词语容易被其底层系统过滤，而真正的危险在于多轮交互中LLMs出于安慰和同理心的尝试所导致的边界逐步侵犯。本文提出了一种多轮压力测试框架，并使用两种压力方法：静态推进和自适应探测，对三个最先进的LLMs进行了长对话安全性测试。我们生成了50个虚拟患者档案，并通过最多20轮的虚拟心理对话对每个模型进行压力测试。实验结果表明，违规行为很常见，两种压力模式产生的违规率相似。然而，自适应探测显著延长了模型跨过边界的时机，将平均轮次从静态推进中的9.21减少到4.64。在两种机制下，做出确定性或零风险承诺是突破边界的最主要方式。这些发现表明，LLMs的安全边界韧性不能仅通过单轮测试推断；必须充分考虑不同交互压力和特征在扩展对话中对安全边界磨损的影响。
英文摘要：
Large language models (LLMs) have been widely used for mental health support. However, current safety evaluations in this field are mostly limited to detecting whether LLMs output prohibited words in single-turn conversations, neglecting the gradual erosion of safety boundaries in long dialogues. Examples include making definitive guarantees, assuming responsibility, and playing professional roles. We believe that with the evolution of mainstream LLMs, words with obvious safety risks are easily filtered by their underlying systems, while the real danger lies in the gradual transgression of boundaries during multi-turn interactions, driven by the LLM's attempts at comfort and empathy. This paper proposes a multi-turn stress testing framework and conducts long-dialogue safety tests on three cutting-edge LLMs using two pressure methods: static progression and adaptive probing. We generated 50 virtual patient profiles and stress-tested each model through up to 20 rounds of virtual psychiatric dialogues. The experimental results show that violations are common, and both pressure modes produced similar violation rates. However, adaptive probing significantly advanced the time at which models crossed boundaries, reducing the average number of turns from 9.21 in static progression to 4.64. Under both mechanisms, making definitive or zero-risk promises was the primary way in which boundaries were breached. These findings suggest that the robustness of LLM safety boundaries cannot be inferred solely through single-turn tests; it is necessary to fully consider the wear and tear on safety boundaries caused by different interaction pressures and characteristics in extended dialogues.
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。
