Shou-De Lin

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks

Data-driven Staircase Activation Functions for Ordinal Classification

Why is the LLM unsure? Profiling the Causes of LLM Uncertainty for Adaptive Model and Uncertainty Metric Selection

Consistent Labeling Across Group Assignments: Variance Reduction in Conditional Average Treatment Effect Estimation

Unpacking In-Context Learning: Underlying Mechanism and Out-of-Distribution Generalization via Blended Training on Function Mixture

Detecting and Perturbing Privacy-Sensitive Neurons to Defend Embedding Inversion Attacks

Think or Remember? Detecting and Directing LLMs Towards Memorization or Generalization

PLHF: Prompt Learning from Few-shot Human Feedback