Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation
Declan Grabb, Max Lamparth, Nina Vasan
TL;DR
The paper addresses the high-stakes challenge of deploying language models in automated mental healthcare by defining a structured Task-Autonomous AI in Mental Healthcare (TAIMH) framework with explicit autonomy levels and ethical default behaviors. It conducts a rigorous, clinician-guided evaluation of 14 state-of-the-art LLMs across 16 mental-health questionnaires to test emergency recognition and safe guidance, finding no model meets clinician standards and many could harm users in crises. The authors propose a two-pronged safety improvement exploration (system-prompt adjustments and self-critique) focused on Llama-2 and fine-tuned models, reporting partial improvements but persistent safety gaps. The work highlights an urgent need for robust safety benchmarks, ethical alignment, and interdisciplinary development to ensure TAIMH can safely scale mental health support and reduce access barriers.
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 questionnaires designed to reflect various mental health conditions, such as psychosis, mania, depression, suicidal thoughts, and homicidal tendencies. The questionnaire 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.