Roy Ka-Wei Lee

A novel approach improves detection of harmful memes using targeted questioning.

Exploring the challenges and strategies for moderating hate speech online.

A novel approach for detecting hateful memes using few-shot learning techniques.

MemeCraft creates engaging memes to promote social causes safely.

SGHateCheck focuses on local languages to tackle online hate speech effectively.

A new framework for verifying authorship with clear explanations.

New dataset provides insights on hate speech across languages and formats.

LongGenBench assesses large language models in generating high-quality long text.

Exploring how AI can help reduce bias in college admissions.

This article examines fairness in admissions using machine learning models.