9 papers · 1 filter
Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation
Drishti Goel, Soorya Ram Shimgekar, Jeongah Lee +4
Refusal is a common safety mechanism in large language models (LLMs), yet in contexts of suicidal ideation (SI), refusing to engage can itself constitute a safety failure. We evalu…
Beyond Counting Blessings: Tracing the Evolution of Gratitude Practices and Technology Needs
Joy Qiuyue Zhong, Jeongah Lee, Drishti Goel +4
Gratitude technologies support well-being by prompting reflection on what people appreciate. But gratitude does not serve the same purpose in every circumstance: as life situations…
Can LLMs identify and repair ruptures? Comparison between clinician practices and LLM behaviors
Jeongah Lee, Joy Qiuyue Zhong, Drishti Goel +4
Ruptures represent common albeit critical moments in interaction where relational alignment breaks down, making them essential for evaluating AI where trust and engagement matter m…
CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem
Jiayue Melissa Shi, Ethan Nguyen, Drishti Goel +7
Family caregivers of people living with dementia shoulder emotional and practical responsibilities, yet their own wellbeing often remains peripheral to dementia care. We built Care…
When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like Caregiver Support
Drishti Goel, Agam Goyal, Veda Duddu +6
Caregivers often turn to online communities for informational and emotional support. In these spaces, peer supporters frequently draw on personal narratives to respond to emotional…
Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles
Drishti Goel, Agam Goyal, Veda Duddu +8
Language models are increasingly being deployed for conversational support in informal caregiving contexts, where interactions often extend beyond information-seeking: caregivers s…
A Taxonomy of Mental Health and Technology Needs for Alzheimer's and Dementia Caregivers
Keran Wang, Drishti Goel, Jiayue Melissa Shi +5
Family members caring for individuals with Alzheimer's disease and related dementias (AD/ADRD) provide the foundation of long-term care worldwide. In 2023, more than 11 million U.S…
Do We Know What They Know We Know? Calibrating Student Trust in AI and Human Responses Through Mutual Theory of Mind
Olivia Pal, Veda Duddu, Agam Goyal +2
Trust and reliance are often treated as coupled constructs in human-AI interaction research, with the assumption that calibrating trust will lead to appropriate reliance. We challe…
RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions
Drishti Goel, Jeongah Lee, Qiuyue Joy Zhong +5
Caregivers seeking AI-mediated support express complex needs---information-seeking, emotional validation, and distress cues---that warrant careful evaluation of response safety and…