arXiv 2502.058792025-02-09cs.CLcs.AI

通过思维链提示增强抑郁症检测：利用大型语言模型从情感分析转向推理分析

Enhancing Depression Detection with Chain-of-Thought Prompting: From Emotion to Reasoning Using Large Language Models

College of Information Science and Engineering, Ritsumeikan University（立命馆大学信息科学与工程学院）；Fujita Health University（藤田医科大学）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）

Shiyu Teng, Jiaqing Liu, Rahul Kumar Jain, Shurong Chai, Ruibo Hou, Tomoko Tateyama, Lanfen Lin, Yen-wei Chen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对当前基于大型语言模型（LLMs）的抑郁症检测方法存在细微症状识别困难、推理过程不透明的问题，提出一种思维链提示方法，将检测分为四阶段，在E-DAIC数据集上验证了其在分类准确性和诊断粒度上的优越性。

摘要：

抑郁症是全球导致残疾的主要原因之一，给个人、医疗系统和整个社会带来了沉重负担。大型语言模型（LLMs）的最新进展在应对心理健康挑战方面展现出潜力，包括通过基于文本的分析检测抑郁症。然而，当前基于LLM的方法往往难以识别细微症状，且缺乏透明的逐步推理过程，导致难以准确分类和解释心理健康状况。为解决这些挑战，我们提出一种思维链提示方法，可同时提升基于LLM的抑郁症检测的性能和可解释性。我们的方法将检测过程分为四个阶段：（1）情感分析；（2）二元抑郁症分类；（3）潜在原因识别；（4）严重程度评估。通过引导模型完成这些结构化推理步骤，我们提高了可解释性，并降低了忽略细微临床指标的风险。我们在E-DAIC数据集上验证了该方法，测试了多个最先进的大型语言模型。实验结果表明，与基线方法相比，我们的思维链提示技术在分类准确性和诊断见解的粒度上均表现更优。

英文摘要：

Depression is one of the leading causes of disability worldwide, posing a severe burden on individuals, healthcare systems, and society at large. Recent advancements in Large Language Models (LLMs) have shown promise in addressing mental health challenges, including the detection of depression through text-based analysis. However, current LLM-based methods often struggle with nuanced symptom identification and lack a transparent, step-by-step reasoning process, making it difficult to accurately classify and explain mental health conditions. To address these challenges, we propose a Chain-of-Thought Prompting approach that enhances both the performance and interpretability of LLM-based depression detection. Our method breaks down the detection process into four stages: (1) sentiment analysis, (2) binary depression classification, (3) identification of underlying causes, and (4) assessment of severity. By guiding the model through these structured reasoning steps, we improve interpretability and reduce the risk of overlooking subtle clinical indicators. We validate our method on the E-DAIC dataset, where we test multiple state-of-the-art large language models. Experimental results indicate that our Chain-of-Thought Prompting technique yields superior performance in both classification accuracy and the granularity of diagnostic insights, compared to baseline approaches.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。