7 papers
Child Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework
Haein Kong
As generative AI is increasingly used by children and adolescents, there is a growing need for risk evaluation frameworks that account for child-specific harms. However, most exist…
FCC: Fully Connected Correlation for One-Shot Segmentation
Seonghyeon Moon, Haein Kong, Muhammad Haris Khan +2
Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for th…
Judging from Support-set: A New Way to Utilize Few-Shot Segmentation for Segmentation Refinement Process
Seonghyeon Moon, Qingze, Liu +2
Segmentation refinement aims to enhance the initial coarse masks generated by segmentation algorithms. The refined masks are expected to capture more details and better contours of…
Persuasion and Safety in the Era of Generative AI
Haein Kong
As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative…
Examining Racial Stereotypes in YouTube Autocomplete Suggestions
Eunbin Ha, Haein Kong, Shagun Jhaver
Autocomplete is a popular search feature that predicts queries based on user input and guides users to a set of potentially relevant suggestions. In this study, we examine what You…
When LLM Therapists Become Salespeople: Evaluating Large Language Models for Ethical Motivational Interviewing
Haein Kong, Seonghyeon Moon
Large language models (LLMs) have been actively applied in the mental health field. Recent research shows the promise of LLMs in applying psychotherapy, especially motivational int…