用提示引导法识别文本中抑郁症状证据，提升罕见症状检测效果
Learning Evidence of Depression Symptoms via Prompt Induction
- 将标注样本压缩为简洁可解释的判断指南，指导大模型分类
- 在21种抑郁症状上整体准确率超主流方法，尤其改善罕见症状识别
- 指南可跨疾病泛化，适用于共病症状分析，适合心理健康研究者
抑郁症给心理健康服务带来巨大压力，许多患者在在线论坛、社交媒体等非临床场景中描述自身体验。自动识别此类文本中的临床症状证据，可弥补临床资源不足并实现大规模筛查。本文针对基于BDI-II量表的21种抑郁症状进行句级分类，构建了标注症状相关性的BDI-Sen数据集。该任务细粒度且高度不平衡，常见大模型方法（零样本、上下文学习、微调）在多数症状上难以保持一致的判别标准。为此提出症状诱导（Symptom Induction, SI）方法，将标注样本提炼为简明可读的判断准则，用于引导分类。在四个大模型家族、八种模型上，SI在BDI-Sen数据集上取得最佳加权F1，对低频症状提升显著。跨领域评估表明，生成的准则可泛化至共享症状特征的其他疾病（双相障碍与进食障碍），具备良好迁移能力。
原文摘要 · Abstract (English)
Depression places substantial pressure on mental health services, and many people describe their experiences outside clinical settings in high-volume user-generated text (e.g., online forums and social media). Automatically identifying clinical symptom evidence in such text can therefore complement limited clinical capacity and scale to large populations. We address this need through sentence-level classification of 21 depression symptoms from the BDI-II questionnaire, using BDI-Sen, a dataset annotated for symptom relevance. This task is fine-grained and highly imbalanced, and we find that common LLM approaches (zero-shot, in-context learning, and fine-tuning) struggle to apply consistent relevance criteria for most symptoms. We propose Symptom Induction (SI), a novel approach which compresses labeled examples into short, interpretable guidelines that specify what counts as evidence for each symptom and uses these guidelines to condition classification. Across four LLM families and eight models, SI achieves the best overall weighted F1 on BDI-Sen, with especially large gains for infrequent symptoms. Cross-domain evaluation on an external dataset further shows that induced guidelines generalize across other diseases shared symptomatology (bipolar and eating disorders).
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。