Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation
Research Area: Evaluation, Societal implications, Safety
Keywords: mental healthcare, automated healthcare, risks, safety evaluation, task-autonomous AI
TL;DR: We discuss structural and ethical considerations for automated mental health care and show that existing models could cause harm if accessed in mental health emergencies using mental questions designed to reflect various mental health symptoms
Abstract: Amidst the growing interest in developing task-autonomous AI for automated mental health care, this paper addresses the ethical and practical challenges associated with the issue and proposes a structured framework that delineates levels of autonomy, outlines ethical requirements, and defines beneficial default behaviors for AI agents in the context of mental health support. We also evaluate fourteen state-of-the-art language models (ten off-the-shelf, four fine-tuned) using 16 mental health-related questions designed to reflect various mental health conditions, such as psychosis, mania, depression, suicidal thoughts, and homicidal tendencies. The question design and response evaluations were conducted by mental health clinicians (M.D.s). We find that existing language models are insufficient to match the standard provided by human professionals who can navigate nuances and appreciate context. This is due to a range of issues, including overly cautious or sycophantic responses and the absence of necessary safeguards. Alarmingly, we find that most of the tested models could cause harm if accessed in mental health emergencies, failing to protect users and potentially exacerbating existing symptoms. We explore solutions to enhance the safety of current models. Before the release of increasingly task-autonomous AI systems in mental health, it is crucial to ensure that these models can reliably detect and manage symptoms of common psychiatric disorders to prevent harm to users. This involves aligning with the ethical framework and default behaviors outlined in our study. We contend that model developers are responsible for refining their systems per these guidelines to safeguard against the risks posed by current AI technologies to user mental health and safety.
Trigger warning: Contains and discusses examples of sensitive mental health topics, including suicide and self-harm.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 1030
Loading