PulseAugur
实时 16:26:24
English(EN) Expert-Level Crisis Detection in Mental Health Conversations

新基准和模型改进心理健康对话中的危机检测

研究人员开发了CRADLE-Dialogue,这是一个用于检测心理健康对话中危机状况的新基准和数据集。该数据集包含600个对话,标注了自杀意念和虐待儿童等各种风险,区分了过去和正在发生的威胁。该研究还引入了一个“警报-确认”评估协议,以更好地反映临床需求,并发布了一个拥有320亿参数的模型,该模型在现有的开源和专有模型方面显示出显著的改进。 AI

影响 增强了AI在敏感对话环境中的能力,有可能改进心理健康支持系统。

排序理由 该集群包含一篇学术论文,详细介绍了用于特定AI任务的新基准、数据集和模型。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Grace Byun, Abigail Lott, Rebecca Lipschutz, Sean T. Minton, Elizabeth A. Stinson, Jinho D. Choi ·

    Expert-Level Crisis Detection in Mental Health Conversations

    arXiv:2606.10380v1 Announce Type: cross Abstract: Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.…

  2. arXiv cs.CL TIER_1 English(EN) · Jinho D. Choi ·

    Expert-Level Crisis Detection in Mental Health Conversations

    Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts. When applied to multi-turn dialogues, current mod…