Saved in:
Bibliographic Details
Main Authors: Abbasi, Mohammad Amin, Mirnezami, Farnaz Sadat, Neshati, Ali, Naderi, Hassan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.05982
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909769133981696
author Abbasi, Mohammad Amin
Mirnezami, Farnaz Sadat
Neshati, Ali
Naderi, Hassan
author_facet Abbasi, Mohammad Amin
Mirnezami, Farnaz Sadat
Neshati, Ali
Naderi, Hassan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05982
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agents
Abbasi, Mohammad Amin
Mirnezami, Farnaz Sadat
Neshati, Ali
Naderi, Hassan
Computation and Language
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.
title HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agents
topic Computation and Language
url https://arxiv.org/abs/2502.05982