Scholar
Wei Jie Yeo
Google Scholar ID: DcUMc_IAAAAJ
PhD candidate, Nanyang Technological University
Citations & Impact
Citations
172
H-index
5
i10-index
3
Publications
10
Co-authors
0
Publications
Resume
Academic Achievements
- - Publications:
- - "Understanding Refusal in Language Models with Sparse Autoencoders" (Preprint, 2025)
- - "Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads" (Preprint, 2025)
- - "A comprehensive review on financial explainable AI" (AIRE Journal, 2025)
- - "Self-training Large Language Models through Knowledge Detection" (EMNLP, 2024)
- - "How Interpretable are Reasoning Explanations from Prompting Large Language Models?" (NAACL, 2024)
- - "Plausible Extractive Rationalization through Semi-Supervised Entailment Signal" (ACL, 2024)
Research Experience
- - PhD Research Project: Focuses on the intersection of NLP and interpretability, especially in the application to AI safety
- - Position: PhD Student
Education
- - Degree: PhD
- - University: Nanyang Technological University (NTU), Singapore
- - Advisor: Prof. Erik Cambria
- - Time: Expected to graduate by the end of 2025
- - Major: Artificial Intelligence
Background
- - Research Interests: Natural Language Processing and Interpretability, AI Safety
- - Professional Field: AI research, particularly improving the understanding of how AI systems model complex behaviors
- - Introduction: Currently a PhD student at Nanyang Technological University, Singapore, focusing on using interpretability to improve AI safety issues such as jailbreak or prompt injection attacks
Miscellany
- - Personal Interests: Not provided