English(EN) Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation

研究：大型语言模型在处理自杀意念披露时常处理不当

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

一篇新发表在arXiv上的研究调查了大型语言模型（LLMs）如何处理自杀意念（SI）的披露。研究发现，LLMs常常拒绝回应SI披露，这本身可能是一种安全上的失败。虽然告知模型SI的背景或抑制拒绝可以增加互动，但并不能可靠地降低响应风险，甚至可能增加风险。然而，一个由临床医生制定的协议，在降低拒绝率的同时，持续地降低了响应风险。 AI

影响凸显了LLM在处理敏感用户披露方面的关键安全漏洞，亟需改进拒绝和互动协议。

排序理由关于LLM安全机制的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 20 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于LLM安全机制的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, paper; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Drishti Goel, Soorya Ram Shimgekar, Jeongah Lee, Violeta J. Rodriguez, Daniel S. Brown, Ravi Karkar, Koustuv Saha · 2026-10-19 04:00

风险与拒绝：LLM 对自杀意念响应的机制

arXiv:2610.22715v1 Announce Type: cross 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…

本文如何被排名

报道来源 [1]

风险与拒绝：LLM 对自杀意念响应的机制

相关实体

相关话题