Shou-De Lin

Full Professor, National Taiwan University

Joined

October 2017

Names

Shou-De Lin

Emails

****@csie.ntu.edu.tw (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Full Professor

National Taiwan University

Present

Full Professor

National Taiwan University (ntu.edu.tw)

2015 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

recommender system

2010 – 2018

unsupervised learning

2010 – 2018

embedding

2010 – 2018

Publications

Consistent Labeling Across Group Assignments: Variance Reduction in Conditional Average Treatment Effect Estimation
Yi-Fu Fu, Keng-Te Liao, Shou-De Lin
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Why is the LLM unsure? Profiling the Causes of LLM Uncertainty for Adaptive Model and Uncertainty Metric Selection
Pei-Fu Guo, Yun-Da Tsai, Shou-De Lin
- Submitted to ICLR 2026
- Readers: Everyone
Unpacking In-Context Learning: Underlying Mechanism and Out-of-Distribution Generalization via Blended Training on Function Mixture
Hung-Chun Huang, Shou-De Lin
- Submitted to ICLR 2026
- Readers: Everyone
Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks
Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin
- ICLR 2026 Poster
- Readers: Everyone
Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
Yu-Che Tsai, Kuan-Yu Chen, Yuan-Chi Li, Yuan-Hao Chen, Ching-Yu Tsai, Shou-De Lin
- ICLR 2026 Poster
- Readers: Everyone
Data-driven Staircase Activation Functions for Ordinal Classification
Guo-Wei Wong, Ming-Chuan Yang, Shou-De Lin, Meng Chang Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Think or Remember? Detecting and Directing LLMs Towards Memorization or Generalization
Yi-Fu Fu, Yu-Chieh Tu, TZU-LING CHENG, Cheng-Yu Lin, Yi-Ting Yang, Heng-Yi Liu, Da-Cheng Juan, Shou-De Lin
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Detecting and Perturbing Privacy-Sensitive Neurons to Defend Embedding Inversion Attacks
Yuche Tsai, Hsiang Hsiao, Shou-De Lin
- Submitted to ICLR 2025
- Readers: Everyone
PLHF: Prompt Learning from Few-shot Human Feedback
Chun-Pai Yang, Sung-En Chang, Shou-De Lin
- Submitted to ICLR 2025
- Readers: Everyone
Towards Optimizing with Large Language Models
Pei-Fu Guo, Ying-Hsuan Chen, Yun-Da Tsai, Shou-De Lin
- KiL 2024 Poster
- Readers: Everyone

View all 55 publications

Co-Authors

View all 111 co-authors