Taesung Lee
Source-listed: Contributor · Meta
- Language models
Selected work
5- Muse Spark Safety & Preparedness ReportContributor · 2026
- Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingAuthor · 2025
- Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuningContributor · 2025
- Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language ModelsContributor · 2023
- Defending Against Machine Learning Model Stealing Attacks Using Deceptive PerturbationsContributor · 2018