中文

AI Content Moderation in Therapy Conversations

人机交互 2026-05-26 v1 人工智能 计算与语言 计算机与社会 社会与信息网络

摘要

Large language models (LLMs) are increasingly being used for emotional support. They are also being developed for formal therapy purposes. However, LLMs like ChaptGPT or Llama are often developed with content moderation guardrails that prevent them from discussing sensitive subjects with users for both liability and safety purposes, and this inability to broach these subjects may affect their capacity as therapists. In this study, we perform an algorithm audit on three state-of-the-art moderation systems (OpenAI's moderation endpoint, Meta's Llama Guard, and Google's Shield Gemma) to investigate the extent to which these systems flag the content of real-life therapy sessions as undesirable. Our results raise implications for the limitations that users and organizations may encounter when designing LLMs to play the part of a therapist.

关键词

引用

@article{arxiv.2605.25454,
  title  = {AI Content Moderation in Therapy Conversations},
  author = {Jiwon Kim and Claire Wang and Taeung Yoon and Sabelle Huang and Koustuv Saha},
  journal= {arXiv preprint arXiv:2605.25454},
  year   = {2026}
}