Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy

2025-10-11

AI Summary

This study investigates whether large language models’ (LLMs’) empathic capabilities exhibit systematic demographic biases across user age, culture, and gender. We introduce the first multidimensional empathic evaluation framework—covering 315 intersecting persona combinations—and assess four leading LLMs along cognitive and affective empathy dimensions using both quantitative scoring and qualitative analysis. Results demonstrate that demographic attributes significantly modulate empathic responses, with compound identities capable of reversing empathy trends; while models broadly mirror real-world empathy patterns, they exhibit pronounced biases—particularly toward Confucian-culture groups. This work provides the first empirical evidence of structural inequity in LLM empathy, establishing a critical benchmark for fair, inclusive empathic AI and identifying concrete pathways for mitigation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Emotional Intelligence
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large Language Models' (LLMs) ability to converse naturally is empowered by their ability to empathetically understand and respond to their users. However, emotional experiences are shaped by demographic and cultural contexts. This raises an important question: Can LLMs demonstrate equitable empathy across diverse user groups? We propose a framework to investigate how LLMs' cognitive and affective empathy vary across user personas defined by intersecting demographic attributes. Our study introduces a novel intersectional analysis spanning 315 unique personas, constructed from combinations of age, culture, and gender, across four LLMs. Results show that attributes profoundly shape a model's empathetic responses. Interestingly, we see that adding multiple attributes at once can attenuate and reverse expected empathy patterns. We show that they broadly reflect real-world empathetic trends, with notable misalignments for certain groups, such as those from Confucian culture. We complement our quantitative findings with qualitative insights to uncover model behaviour patterns across different demographic groups. Our findings highlight the importance of designing empathy-aware LLMs that account for demographic diversity to promote more inclusive and equitable model behaviour.

Problem

• Investigating LLM empathy variations across diverse demographic personas
• Assessing equitable empathetic responses across age, culture, and gender
• Identifying demographic biases in LLMs' cognitive and affective empathy

Innovation

• Intersectional demographic analysis of empathy
• Multi-attribute persona framework for LLM evaluation
• Quantitative and qualitative empathy pattern investigation