风险与拒答：LLM 回应自杀意念的机制
Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation
一项预印本研究评估了八个指令微调大语言模型在三个数据集上对自杀意念与自伤披露的回应，并对六个开放权重模型做机制分析（依据摘要，未完成同行评审）。结果显示，基线时回应风险升高主要源于对披露的忽视以及拒答；告知模型披露涉及自杀意念或直接抑制拒答，会增加互动但未必降低风险，甚至可能升高风险；而临床医生制定的回应协议在降低拒答的同时持续降低回应层面风险。
在三个数据集上测试八种指令微调大模型对自杀意念披露的回应，并对六个开放权重模型做机制分析，比较告知情境与临床方案的作用。
arXiv:2610.22715v1 Announce Type: new Abstract: Refusal is a common safety mechanism in large language models (LLMs), yet in contexts of suicidal ideation (SI), refusing to engage can itself constitute a safety failure. We evaluate how eight instruction-tuned LLMs respond to SI and self-harm disclosures across three datasets, varying whether models are informed that a disclosure expresses SI and whether they receive a clinician-developed response protocol, and complement this with mechanistic analyses in six open-weight models. Our results reveal a nuanced relationship between refusal and response-level risk. At baseline, elevated risk in model responses is driven primarily by inattention to the disclosure, alongside refusal to engage. Mechanistic analyses suggest that models may refuse SI disclosures through the same direction that mediates their refusals of harmful requests. However, informing models of the SI context, or suppressing refusal directly, increases engagement without reliably lowering response risk, and may raise it. In contrast, the clinician-guided protocol consistently reduces response-level risk while also reducing refusal. Together, these analyses and ablations motivate the need for models that refuse only when warranted and engage in interactionally safe ways when users disclose SI.
中文翻译还没有生成，先显示原文。
来源：arXiv · Human-Computer Interaction · arxiv.org