# Customizing Emotional Support: How Do Individuals Construct and Interact With LLM-Powered Chatbots

arXiv: https://arxiv.org/abs/2504.12943 · HTML: https://mlsanity.com/paper/2504.12943/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2025.

## Built on by (most cited first, 25 of 25)

- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [Beyond Data Privacy: New Privacy Risks for Large Language Models](https://mlsanity.com/paper/2509.14278/) (2025)
- [Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving](https://mlsanity.com/paper/2504.17999/) (2025)
- [Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs](https://mlsanity.com/paper/2508.16921/) (2025)
- [EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World](https://mlsanity.com/paper/2601.01530/) (2026)
- [Does My Chatbot Have an Agenda? Understanding Human and AI Agency in Human-Human-like Chatbot Interaction](https://mlsanity.com/paper/2601.22452/) (2026)
- [GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing](https://mlsanity.com/paper/2606.00860/) (2026)
- [Privacy in Human-AI Romantic Relationships: Concerns, Boundaries, and Agency](https://mlsanity.com/paper/2601.16824/) (2026)
- [AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations](https://mlsanity.com/paper/2601.22440/) (2026)
- [Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles](https://mlsanity.com/paper/2605.29473/) (2026)
- [Bias Beneath the Tone: Empirical Characterisation of Tone Bias in LLM-Driven UX Systems](https://mlsanity.com/paper/2512.19950/) (2025)
- [Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers](https://mlsanity.com/paper/2601.07698/) (2026)
- [Polite But Boring? Trade-offs Between Engagement and Psychological Reactance to Chatbot Feedback Styles](https://mlsanity.com/paper/2601.20683/) (2026)
- [Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild](https://mlsanity.com/paper/2605.05767/) (2026)
- [IntentGrasp: A Comprehensive Benchmark for Intent Understanding](https://mlsanity.com/paper/2605.06832/) (2026)
- [Designing Proactive Thought Partners for Writing](https://mlsanity.com/paper/2609.01588/) (2026)
- [Balancing Efficiency and Empathy: Healthcare Providers' Perspectives on AI-Supported Workflows for Serious Illness Conversations in the Emergency Department](https://mlsanity.com/paper/2506.00241/) (2025)
- [Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being](https://mlsanity.com/paper/2511.05769/) (2025)
- [Generative Confidants: How do People Experience Trust in Emotional Support from Generative AI?](https://mlsanity.com/paper/2601.16656/) (2026)
- [CounselReflect: Opportunities and Challenges for Designing Tools to Support Self-Reflection on Mental Health and Well-Being Conversations with AI](https://mlsanity.com/paper/2603.29429/) (2026)
- [Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation](https://mlsanity.com/paper/2604.17178/) (2026)
- [Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers](https://mlsanity.com/paper/2604.20166/) (2026)
- [When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like Caregiver Support](https://mlsanity.com/paper/2606.18057/) (2026)
- [I wanted it to feel more personal: Customization of social AI as AI individualism in practice](https://mlsanity.com/paper/2607.17826/) (2026)
- [From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study](https://mlsanity.com/paper/2609.16344/) (2026)

## Abstract (arXiv)

Personalized support is essential to fulfill individuals' emotional needs and sustain their mental well-being. Large language models (LLMs), with great customization flexibility, hold promises to enable individuals to create their own emotional support agents. In this work, we developed ChatLab, where users could construct LLM-powered chatbots with additional interaction features including voices and avatars. Using a Research through Design approach, we conducted a week-long field study followed by interviews and design activities (N = 22), which uncovered how participants created diverse chatbot personas for emotional reliance, confronting stressors, connecting to intellectual discourse, reflecting mirrored selves, etc. We found that participants actively enriched the personas they constructed, shaping the dynamics between themselves and the chatbot to foster open and honest conversations. They also suggested other customizable features, such as integrating online activities and adjustable memory settings. Based on these findings, we discuss opportunities for enhancing personalized emotional support through emerging AI technologies.