HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agents
This work addresses the need for culturally sensitive AI-assisted mental health support in underrepresented Persian-speaking communities.
The authors tackled the problem of creating a culturally adapted Persian-language dataset for AI-assisted mental health support, resulting in HamRaz, which outperforms existing baselines in empathy, coherence, and realism. Human evaluations show the effectiveness of HamRaz in capturing the ambiguity and emotional nuance of Persian-speaking clients.
We present HamRaz, a culturally adapted Persian-language dataset for AI-assisted mental health support, grounded in Person-Centered Therapy (PCT). To reflect real-world therapeutic challenges, we combine script-based dialogue with adaptive large language models (LLM) role-playing, capturing the ambiguity and emotional nuance of Persian-speaking clients. We introduce HamRazEval, a dual-framework for assessing conversational and therapeutic quality using General Metrics and specialized psychological relationship measures. Human evaluations show HamRaz outperforms existing baselines in empathy, coherence, and realism. This resource contributes to the Digital Humanities by bridging language, culture, and mental health in underrepresented communities.