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

2026-04-15

AI Summary

This study addresses the limitations of large language models in mental health counseling, particularly their frequent lack of cultural sensitivity, contextual appropriateness, and clinical guidance. Focusing on the Bangladeshi context, the authors developed a culturally adapted knowledge graph through multidisciplinary expert collaboration, manual curation, and clinical validation. This knowledge graph was integrated with retrieval-augmented generation (RAG) and knowledge graph–based reasoning to enhance model responses. Experimental results demonstrate that, compared to standard RAG alone, the proposed approach significantly improves the contextual relevance, clinical appropriateness, and practical usability of generated responses, effectively mitigating critical shortcomings of general-purpose large language models in cross-cultural psychological counseling.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• mental health counseling
• cultural sensitivity
• clinically validated knowledge
• large language models
• contextual grounding

Innovation

• knowledge graph
• retrieval-augmented generation
• culturally-grounded counseling
• large language models
• clinical validation