This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.
📄 Paper
🌐 Webpage
Abstract
Large language models (LLMs) show promise in offering emotional support and generating empathetic responses for individuals in distress, but their ability to deliver culturally sensitive support remains underexplored due to lack of resources. In this work, we introduce CultureCare, the first dataset designed for this task, spanning four cultures and including 1729 distress messages, 1523 cultural signals, and 1041 support strategies with fine-grained emotional and cultural annotations. Leveraging CultureCare, we (i) develop and test four adaptation strategies for guiding three state-of-the-art LLMs toward culturally sensitive responses; (ii) conduct comprehensive evaluations using LLM judges, in-culture human annotators, and clinical psychologists; (iii) show that adapted LLMs outperform anonymous online peer responses, and that simple cultural role-play is insufficient for cultural sensitivity; and (iv) explore the application of LLMs in clinical training, where experts highlight their potential in fostering cultural competence in future therapists.
To use the repository, please see the README.md file in arxiv2025_culturecare folder here.
This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.
If you find this repository useful, please cite the following paper:
@article{culturecare2025,
author = {Chen Cecilia Liu and
Hiba Arnaout and
Nils Kovačić and
Dana Atzil-Slonim and
Iryna Gurevych},
title = {Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity},
note = {Chen Cecilia Liu and Hiba Arnaout contributed equally to this work},
journal = {ArXiv preprint},
year = {2025},
url = {https://arxiv.org/abs/2508.07902},
doi = {https://doi.org/10.48550/arXiv.2508.07902},
eprinttype = {arXiv},
eprint = {2508.07902}
}
https://www.ukp.tu-darmstadt.de/
Don't hesitate to send first authors an e-mail if something is broken (and it shouldn't be) or if you have further questions.