用专家验证的知识图谱提升AI心理咨询的文化适配性
Enhancing Mental Health Counseling Support in Bangladesh using Culturally-Grounded Knowledge
- 构建临床验证的知识图谱，关联压力源、干预与效果
- 知识图谱方法在多指标评测中显著优于单纯检索增强
- 适合需要文化敏感度的心理健康支持系统开发者
大语言模型（LLMs）在心理健康咨询中展现潜力，但其回应常缺乏文化敏感性、上下文相关性和临床适当性。本文系统探讨如何将领域特异、临床验证的知识融入LLMs以提升咨询质量。我们比较了两种方法：检索增强生成（RAG）和基于知识图谱（KG）的方法，后者由跨学科团队手工构建并经临床验证，捕捉压力源、干预措施与结果间的因果关系。在多个LLM上，通过BERTScore F1、SBERT余弦相似度及五项人类评估指标（涵盖有效性、相关性、临床适当性等）进行测试。结果表明，知识图谱方法在上下文相关性、临床适当性和实际可用性方面均显著优于仅使用RAG的模型，证明结构化专家知识对克服LLMs在咨询任务中的局限至关重要。
原文摘要 · Abstract (English)
Large language models (LLMs) show promise in generating supportive responses for mental health and counseling applications. However, their responses often lack cultural sensitivity, contextual grounding, and clinically appropriate guidance. This work addresses the gap of how to systematically incorporate domain-specific, clinically validated knowledge into LLMs to improve counseling quality. We utilize and compare two approaches, retrieval-augmented generation (RAG) and a knowledge graph (KG)-based method, designed to support para-counselors. Our KG is constructed manually and clinically validated, capturing causal relationships between stressors, interventions, and outcomes, with contributions from multidisciplinary people. We evaluated multiple LLMs in both settings using BERTScore F1 and SBERT cosine similarity, as well as human evaluation across five metrics, which is designed to directly measure the effectiveness of counseling beyond similarity at the surface level. The results show that KG-based approaches consistently improve contextual relevance, clinical appropriateness, and practical usability compared to RAG alone, demonstrating that structured, expert-validated knowledge plays a critical role in addressing LLMs limitations in counseling tasks.
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。