Beyond the Single Turn: Reframing Refusals as Dynamic Experiences Embedded in the Context of Mental Health Support Interactions with LLMs

TL;DR

This study explores how large language model refusals in mental health support are experienced as complex, multi-phase interactions, emphasizing the need for holistic evaluation and improved refusal mechanisms.

Contribution

It introduces a multi-phase framework for understanding LLM refusals in mental health contexts, moving beyond simple binary assessments.

Findings

Refusals are multi-phase, dynamic experiences rather than isolated responses.

Users and professionals interpret refusals within broader support-seeking trajectories.

Design recommendations aim to improve future refusal mechanisms.

Abstract

Content Warning: This paper contains participant quotes and discussions related to mental health challenges, emotional distress, and suicidal ideation. Large language models (LLMs) are increasingly used for mental health support, yet the model safeguards -- particularly refusals to engage with sensitive content -- remain poorly understood from the perspectives of users and mental health professionals (MHPs) and have been reported to cause real-world harms. This paper presents findings from a sequential mixed-methods study examining how LLM refusals are experienced and interpreted in mental health support interactions. Through surveys (N=53) and in-depth interviews (N=16) with individuals using LLMs for mental health support and MHPs, we reveal that refusals are not isolated, single-turn system behaviors but rather constitute dynamic, multi-phase experiences: pre-refusal expectation formation, refusal triggering and encounter, refusal message framing, resource referral provision, and post-refusal outcomes. We contribute a multi-phase framework for evaluating refusals beyond binary policy compliance accuracy and design recommendations for future refusal mechanisms. These findings suggest that understanding LLM refusals requires moving beyond single-turn interactions toward recognizing them as holistic experiences embedded within users' support-seeking trajectories and the broader LLM design pipeline.