Saved in:
Bibliographic Details
Main Authors: Chen, Lucia, Preece, David A., Sikka, Pilleriin, Gross, James J., Krause, Ben
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.11387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917723096743936
author Chen, Lucia
Preece, David A.
Sikka, Pilleriin
Gross, James J.
Krause, Ben
author_facet Chen, Lucia
Preece, David A.
Sikka, Pilleriin
Gross, James J.
Krause, Ben
contents Large language model (LLM) chatbots are susceptible to biases and hallucinations, but current evaluations of mental wellness technologies lack comprehensive case studies to evaluate their practical applications. Here, we address this gap by introducing the MHealth-EVAL framework, a new role-play based interactive evaluation method designed specifically for evaluating the appropriateness, trustworthiness, and safety of mental wellness chatbots. We also introduce Psyfy, a new chatbot leveraging LLMs to facilitate transdiagnostic Cognitive Behavioral Therapy (CBT). We demonstrate the MHealth-EVAL framework's utility through a comparative study of two versions of Psyfy against standard baseline chatbots. Our results showed that Psyfy chatbots outperformed the baseline chatbots in delivering appropriate responses, engaging users, and avoiding untrustworthy responses. However, both Psyfy and the baseline chatbots exhibited some limitations, such as providing predominantly US-centric resources. While Psyfy chatbots were able to identify most unsafe situations and avoid giving unsafe responses, they sometimes struggled to recognize subtle harmful intentions when prompted in role play scenarios. Our study demonstrates a practical application of the MHealth-EVAL framework and showcases Psyfy's utility in harnessing LLMs to enhance user engagement and provide flexible and appropriate responses aligned with an evidence-based CBT approach.
format Preprint
id arxiv_https___arxiv_org_abs_2407_11387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Framework for Evaluating Appropriateness, Trustworthiness, and Safety in Mental Wellness AI Chatbots
Chen, Lucia
Preece, David A.
Sikka, Pilleriin
Gross, James J.
Krause, Ben
Human-Computer Interaction
Large language model (LLM) chatbots are susceptible to biases and hallucinations, but current evaluations of mental wellness technologies lack comprehensive case studies to evaluate their practical applications. Here, we address this gap by introducing the MHealth-EVAL framework, a new role-play based interactive evaluation method designed specifically for evaluating the appropriateness, trustworthiness, and safety of mental wellness chatbots. We also introduce Psyfy, a new chatbot leveraging LLMs to facilitate transdiagnostic Cognitive Behavioral Therapy (CBT). We demonstrate the MHealth-EVAL framework's utility through a comparative study of two versions of Psyfy against standard baseline chatbots. Our results showed that Psyfy chatbots outperformed the baseline chatbots in delivering appropriate responses, engaging users, and avoiding untrustworthy responses. However, both Psyfy and the baseline chatbots exhibited some limitations, such as providing predominantly US-centric resources. While Psyfy chatbots were able to identify most unsafe situations and avoid giving unsafe responses, they sometimes struggled to recognize subtle harmful intentions when prompted in role play scenarios. Our study demonstrates a practical application of the MHealth-EVAL framework and showcases Psyfy's utility in harnessing LLMs to enhance user engagement and provide flexible and appropriate responses aligned with an evidence-based CBT approach.
title A Framework for Evaluating Appropriateness, Trustworthiness, and Safety in Mental Wellness AI Chatbots
topic Human-Computer Interaction
url https://arxiv.org/abs/2407.11387