Enhancing Mental Health Counseling Support in Bangladesh using Culturally-Grounded Knowledge

TL;DR

This paper explores integrating clinically validated, culturally-sensitive knowledge into large language models to improve mental health counseling support in Bangladesh, comparing retrieval-augmented generation and knowledge graph methods.

Contribution

It introduces a manually constructed, clinically validated knowledge graph and demonstrates its effectiveness over RAG in enhancing counseling quality.

Findings

Knowledge graph approach improves contextual relevance and clinical appropriateness.

KG-based methods outperform RAG in human evaluations.

Structured expert-validated knowledge enhances LLMs in sensitive applications.

Abstract

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.