Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recovery
Ryuhaerang Choi, Taehan Kim, Subin Park, Jennifer G. Kim, Sung-Ju Lee
摘要
Eating disorders (ED) are complex mental health conditions that require long-term management and support. Recent advancements in large language model (LLM)-based chatbots offer the potential to assist individuals in receiving immediate support. Yet, concerns remain about their reliability and safety in sensitive contexts such as ED. We explore the opportunities and potential harms of using LLM-based chatbots for ED recovery. We observe the interactions between 26 participants with ED and an LLM-based chatbot, WellnessBot, designed to support ED recovery, over 10 days. We discovered that our participants have felt empowered in recovery by discussing ED-related stories with the chatbot, which served as a personal yet social avenue. However, we also identified harmful chatbot responses, especially concerning individuals with ED, that went unnoticed partly due to participants’ unquestioning trust in the chatbot’s reliability. Based on these findings, we provide design implications for safe and effective LLM-based interventions in ED management.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- Opportunities and Barriers for AI Feedback on Meeting Inclusion in Socioorganizational TeamsMo Houtti, Moyan Zhou, Daniel Runningen, Surabhi Sunil 等CHI 2026 · 被引用 3 次
- From Daily Song to Daily Self: Supporting Emotional Growth of Deaf and Hard-of-Hearing Individuals through Generative AI SongwritingYoujin Choi, Jinyoung Yoo, JaeYoung Moon, Yoonjae Kim 等CHI 2026 · 被引用 2 次
- Recovery is Relational: Digital Support Needs for Patients and Supporters in Eating Disorder RecoveryRyuhaerang Choi, Seohyeon Yoo, Xuhai Xu, Sung-Ju LeeCHI 2026 · 被引用 2 次
- Designing a Generative AI-Assisted Music Psychotherapy Tool for Deaf and Hard-of-Hearing IndividualsYoujin Choi, JaeYoung Moon, Jinyoung Yoo, Jennifer G. Kim 等CHI 2026 · 被引用 2 次
- From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating DisordersAmy A. Winecoff, Kevin KlymanCHI 2026
它引用的顶会 Paper19
- "I Hear You, I Feel You": Encouraging Deep Self-disclosure through a ChatbotYi-Chieh Lee, Naomi Yamashita, Yun Huang, Wai FuCHI 2020 · 被引用 333 次
- Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text DataXuhai Xu, Bingsheng Yao, Yuanzhe Dong, Saadia Gabriel 等UbiComp 2024 · 被引用 281 次
- MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' JournalingTaewan Kim, Seolyeong Bae, Hyun Ah Kim, Su-Woo Lee 等CHI 2024 · 被引用 112 次
- "It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational AgentsZhiping Zhang, Michelle Jia, Hao-Ping (Hank) Lee, Bingsheng Yao 等CHI 2024 · 被引用 92 次
- Unlock Life with a Chat(GPT): Integrating Conversational AI with Large Language Models into Everyday Lives of Autistic IndividualsDasom Choi, Sunok Lee, Sung-In Kim, Kyungah Lee 等CHI 2024 · 被引用 78 次
相关 Paper
- The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health SupportInhwa Song, Sachin R. Pendse, Neha Kumar, Munmun De ChoudhuryCSCW 2025 · 被引用 41 次
- A Conditional Companion: Lived Experiences of People with Mental Health Disorders Using LLMs: Conditional Companion: LLMs & Mental HealthAditya Kumar Purohit, Hendrik HeuerCHI 2026 · 被引用 3 次
- Understanding the Benefits and Challenges of Deploying Conversational AI Leveraging Large Language Models for Public Health InterventionEunkyung Jo, Daniel A. Epstein, Hyunhoon Jung, Young-Ho KimCHI 2023 · 被引用 167 次
- Understanding the Impact of Long-Term Memory on Self-Disclosure with Large Language Model-Driven Chatbots for Public Health InterventionEunkyung Jo, Yuin Jeong, SoHyun Park, Daniel A. Epstein 等CHI 2024 · 被引用 71 次
- Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental HealthJabari Kwesi, Jiaxun Cao, Riya Manchanda, Pardis Emami NaeiniUSENIX Security 2025
