Chan Young Park

Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability

Beyond Similarity for Personalization: User Memory Selection via Response-Utility Optimization

Reasoning Up the Instruction Ladder for Controllable Language Models

PrefPalette: Personalized Preference Modeling with Latent Attributes

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring (the Lack of) Cultural Knowledge of LLMs