Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity

Chen Cecilia Liu; Hiba Arnaout; Nils Kovačić; Dana Atzil-Slonim; Iryna Gurevych

doi:10.18653/v1/2026.eacl-long.25

Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity (2026.eacl-long)

Copied to clipboard

Chen Cecilia Liu, Hiba Arnaout, Nils Kovačić, Dana Atzil-Slonim, Iryna Gurevych

Large language models

LLMs

adaptation strategies

LLM-as-a-Judge

cultural sensitivity

clinical training

Challenge:	Large language models (LLMs) have shown growing potential in offering emotional support, but their ability to deliver culturally sensitive support remains underexplored due to a lack of resources.
Approach:	They propose a large language model dataset that includes 1,729 distress messages, 1,523 cultural signals and 1,041 support strategies with fine-grained emotional and cultural annotations.
Outcome:	The proposed models outperform peer-reviewed models and lack cultural sensitivity.

Similar Papers

Overview

Challenge

Approach

Outcome

Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models (2025.naacl-long)

Copied to clipboard

Somnath Banerjee, Sayan Layek, Hari Shrawgi, Rajarshi Mandal, Avik Halder, Shanu Kumar, Sagnik Basu, Parag Agrawal, Rima Hazra, Animesh Mukherjee

Semantic Text Processing

Challenge:	Cultural harm arises when LLMs misrepresent or normalize values, identities, and practices in ways that conflict with the norms of diverse cultural groups.
Approach:	They propose a cultural harm test dataset and a preference dataset to assess model outputs across different cultural contexts.
Outcome:	The proposed model improves model behavior significantly reducing the likelihood of generating culturally insensitive or harmful content.

The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth (2024.naacl-long)

Copied to clipboard

Shir Lissak, Nitay Calderon, Geva Shenkman, Yaakov Ophir, Eyal Fruchter, Anat Brunstein Klomek, Roi Reichart

Challenge:	Queer youth face increased mental health risks, such as depression, anxiety, and suicidal ideation.
Approach:	They propose a scale that is inspired by psychological standards and expert input to evaluate LLM's interactions with queer-related content.
Outcome:	The proposed scale outperforms human responses to queer-related content and outperformed LLMs in the qualitative and quantitative analysis.

Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment (2025.findings-emnlp)

Copied to clipboard

Priyanka Dey, Aayush Bothra, Yugal Khanter, Jieyu Zhao, Emilio Ferrara

Challenge:	Recent studies have explored personality evaluation of LLMs, but they largely overlook the interplay between culture and personality.
Approach:	They propose a large-scale benchmark for evaluating LLMs’ personality expression in culturally grounded, behaviorally rich contexts.
Outcome:	The proposed benchmark improves alignment with country-specific human personality distributions and elicits more expressive, culturally coherent outputs compared to existing benchmarks.

Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model’s Empathy (2025.findings-emnlp)

Copied to clipboard

Ananya Malik, Nazanin Sabri, Melissa M. Karnaze, Mai ElSherief

Challenge:	Large Language Models’ ability to converse naturally is empowered by their ability to empathetically understand and respond to their users.
Approach:	They propose a framework to investigate how LLMs’ cognitive and affective empathy vary across user personas defined by intersecting demographic attributes.
Outcome:	The proposed framework examines 315 unique personas from age, culture, and gender across four LLMs.

SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)

Copied to clipboard

Yirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng, Zhenyu Wang, Qi Liu, Xiangmin Xu

Language Models

Challenge:	Large language models (LLMs) are used in psychological counseling to provide universal advice.
Approach:	They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning .
Outcome:	Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues .

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations (2025.emnlp-main)

Copied to clipboard

Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

Dialogue Systems & Conversational Agents

Challenge:	Experimental results show that LLMs can infer persona traits and subtle shifts in emotionality and extraversion occur . scalable solutions with reduced costs and enhanced data privacy are needed .
Approach:	They explore the role of personas in the creation of emotional support conversations by LLMs.
Outcome:	The proposed model can infer persona traits and maintain key persona characteristics while revealing shifts in emotionality and extraversion.

Hate Personified: Investigating the role of LLMs in content moderation (2024.emnlp-main)

Copied to clipboard

Sarah Masud, Sahajpreet Singh, Viktor Hangya, Alexander Fraser, Tanmoy Chakraborty

Responsible & Trustworthy NLP

Challenge:	Our work provides preliminary guidelines and highlights the nuances of applying Large Language models in culturally sensitive cases.
Approach:	They propose to use large language models to help with content moderation to assess how well the needs of diverse groups are reflected in annotated posts.
Outcome:	The proposed model is able to leverage community-based flagging efforts and exposure to adversaries.

Cultural Learning-Based Culture Adaptation of Language Models (2025.acl-long)

Copied to clipboard

Chen Cecilia Liu, Anna Korhonen, Iryna Gurevych

Language Models

Challenge:	Existing approaches for adapting large language models to diverse cultural values often rely on prompt engineering.
Approach:	They propose a framework for enhancing LLM alignment with cultural values based on cultural learning that leverages simulated social interactions to generate role-playing scenarios.
Outcome:	The proposed framework improves cultural value alignment across various model architectures measured using World Value Survey data.

Can Machines Resonate with Humans? Evaluating the Emotional and Empathic Comprehension of LMs (2024.findings-emnlp)

Copied to clipboard

Muhammad Arslan Manzoor, Yuxia Wang, Minghan Wang, Preslav Nakov

Language Models

Challenge:	Empathy plays a pivotal role in fostering prosocial behavior, often triggered by the sharing of personal experiences through narratives.
Approach:	They propose to use contrastive learning with masked LMs and supervised fine-tuning with large language models to improve empathy understanding in NLP models.
Outcome:	The proposed methods show that there is low agreement among annotators and that cultural differences are a factor in their interpretation of empathy.

I Don’t Need Solution. I Need Emotional Support : Empathetic LLMs based on Emotional Validation (2026.findings-acl)

Copied to clipboard

Suhyune Son, Jungwoo Lim, Myunghoon Kang, Seongtae Hong, Yuna Hur, Evelyn H. Zi, Heuiseok Lim

Text Generation

Challenge:	Existing large language models (LLMs) struggle to generate emotional support response, despite observing and reflecting on the help-seeker’s situation . Empathy drives the formation of constructive interpersonal and supportive relationships, including counseling for mental health care .
Approach:	They propose to use a two-stage training process to enhance empathetic response generation through empathy acquisition and emotional validation alignment.
Outcome:	The proposed method significantly improves empathetic response generation, achieving superior performance in both automatic and human evaluations.