15 papers
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…
FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents
Srihari Unnikrishnan, Jaskaran Singh Walia, Drishti Goel +1
Cloud services experience frequent incidents that require rapid diagnosis and resolution. Troubleshooting guides help engineers respond consistently, but creating them manually is…
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…
eARCO: Efficient Automated Root Cause Analysis with Prompt Optimization
Drishti Goel, Raghav Magazine, Supriyo Ghosh +5
Root cause analysis (RCA) for incidents in large-scale cloud systems is a complex, knowledge-intensive task that often requires significant manual effort from on-call engineers (OC…
Time Warp: The Gap Between Developers' Ideal vs Actual Workweeks in an AI-Driven Era
Sukrit Kumar, Drishti Goel, Thomas Zimmermann +3
Software developers balance a variety of different tasks in a workweek, yet the allocation of time often differs from what they consider ideal. Identifying and addressing these dev…
Machine Learning Interventions for Weed Detection using Multispectral Imagery and Unmanned Aerial Vehicles -- A Systematic Review
Drishti Goel, Bhavya Kapur, Prem Prakash Vuppuluri
The growth of weeds poses a significant challenge to agricultural productivity, necessitating efficient and accurate weed detection and management strategies. The combination of mu…
PRECISe : Prototype-Reservation for Explainable Classification under Imbalanced and Scarce-Data Settings
Vaibhav Ganatra, Drishti Goel
Deep learning models used for medical image classification tasks are often constrained by the limited amount of training data along with severe class imbalance. Despite these probl…
X-lifecycle Learning for Cloud Incident Management using LLMs
Drishti Goel, Fiza Husain, Aditya Singh +5
Incident management for large cloud services is a complex and tedious process and requires significant amount of manual efforts from on-call engineers (OCEs). OCEs typically levera…