发表机构
Wysa Inc.（Wysa公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究数字心理健康干预中，通过在名为Wysa的DMHI里对比启用和禁用检索增强生成（RAG）模式，评估六个大语言模型，计算相关指标并测试差异，发现RAG虽致误报增加，但符合安全原则，是提升LLM驱动的DMHIs相关性能的有前景方法。
AI 中文摘要
数字心理健康干预（DMHIs）提供了可扩展的支持，但在不稳定情况下确保准确检测用户意图具有挑战性。纯参数化大语言模型（LLMs）缺乏特定安全关键架构，可能错过关键线索或产生幻觉，影响可靠性。检索增强生成（RAG）可补充LLM的检索上下文，增强不稳定情况下的意图检测。商业DMHIs通常组合多个独立安全层，但单个层的增量贡献未量化。本文在名为Wysa的DMHI中评估六个LLM模型，通过启用和禁用RAG模式的对比。匿名真实和合成用户-聊天机器人交流由专业临床团队针对多类意图类别标注。计算分类准确率、召回率、精确率和F1分数并测试差异显著性。还按风险类别和模型间一致性检查性能。虽然RAG导致误报增加，但权衡符合优先考虑敏感性的安全关键设计原则。总体而言，这些发现支持RAG是提高LLM驱动的DMHIs准确性、一致性和安全性的有前景方法。
英文摘要
Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging. Pure parametric Large Language models (LLMs) do not contain specific safety critical architecture, and can miss critical cues, or hallucinate, undermining reliability. Retrieval Augmented Generation (RAG), which supplements an LLM with retrieved context, could enhance intent detection during volatile situations. Commercially available DMHIs typically combine multiple independent safety layers like rule-based filters, symbolic escalation protocols, and neural classification. The incremental contribution of any single layer, however, remains unquantified. This paper evaluates six LLM models within a DMHI called Wysa, via a controlled comparison of RAG-enabled versus RAG-disabled modes. Anonymized real and synthetic user-chatbot exchanges were annotated by a qualified clinical team against multi-class intent categories (e.g. self-harm, abuse, panic). The study computed classification accuracy, recall, precision and F1 scores against ground truth labels and tested differences for statistical significance. Performance was also examined by risk category and inter-model agreement. While RAG caused a rise in false alarms, the trade-off is consistent with safety-critical design principles that prioritize sensitivity, where flagged cases are routed to additional review rather than acted on directly. Overall, these findings support RAG as a promising approach to improve the accuracy, consistency and safety of LLM-driven DMHIs. Keywords: Digital Mental Health Intervention, Large Language Model, Retrieval Augmented Generation, Accuracy, Recall, Precision
Comments11 pages, 6 figures
