用大模型自动评估心理危机等级，提升热线服务效率与准确性
Speech-based Psychological Crisis Assessment using LLMs
- 将语音中的情绪线索注入文本，让大模型理解声音背后的语气
- 通过推理链训练提升分类准确率，三分类任务F1达0.802
- 适合心理热线系统开发者、医疗AI研究者参考
心理支持热线在应对心理健康危机中发挥关键作用，但当前评估仍依赖人工，易受经验差异和人力限制影响。本文提出基于大语言模型（LLM）的自动化危机等级分类框架。为更好捕捉口语对话中的情感信号，引入一种声学特征注入方法，将识别出的非语言情绪线索插入语音转录文本，使大模型能融合声音中的情感细节。同时，设计一种增强推理的训练策略，让模型生成诊断推理链条作为辅助任务，起到正则化作用，提升分类性能。结合数据增强，最终系统在三分类任务中达到宏平均F1分数0.802，准确率0.805（5折交叉验证）。
原文摘要 · Abstract (English)
Psychological support hotlines provide critical support for individuals experiencing mental health emergencies, yet current assessments largely rely on human operators whose judgments may vary with professional experience and are constrained by limited staffing resources. This paper proposes a large language model (LLM)-based framework for automated crisis level classification, a key indicator that supports many downstream tasks and improves the overall quality of hotline services. To better capture emotional signals in spoken conversations, we introduce a paralinguistic injection method that inserts identified non-verbal emotional cues into speech transcripts, enabling LLM-based reasoning to incorporate critical acoustic nuances. In addition, we propose a reasoning-enhanced training strategy that trains the model to generate diagnostic reasoning chains as an auxiliary task, which serves as a regulariser to improve classification performance. Combined with data augmentation, our final system achieves a macro F1-score of 0.802 and an accuracy of 0.805 on the three-class classification task under 5-fold cross-validation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。