The field of human-AI interaction is rapidly evolving, with a growing focus on improving the cultural responsiveness and empathy of large language models (LLMs) in mental health support applications. Recent studies have demonstrated the effectiveness of cultural prompting in enhancing the cultural responsiveness of LLM-generated therapeutic responses, highlighting the importance of cultural sensitivity in delivering empathetic AI-based therapeutic interventions. Furthermore, research has explored the use of LLMs as mediators in online conflicts, with promising results in fostering empathy and constructive dialogue. The development of digital therapeutic companion agents has also shown potential in improving depressive symptoms and quality of life, with high adherence rates and significant reductions in depressive symptoms. Noteworthy papers include 'Cultural Prompting Improves the Empathy and Cultural Responsiveness of GPT-Generated Therapy Responses', which demonstrated the effectiveness of cultural prompting in improving cultural responsiveness, and 'From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars?', which explored the potential of LLMs as mediators in online conflicts.