Scholar
Xilin Gong
Google Scholar ID: rlQK1HUAAAAJ
University of Georgia
Interpretability of LLM
Trustworthy Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
28
H-index
3
i10-index
2
Publications
6
Co-authors
5
list available
Publications
8 items
STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems
2026
Cited
0
Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models
2026
Cited
0
Investigating CoT Monitorability in Large Reasoning Models
2025
Cited
0
MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
2025
Cited
0
When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
2025
Cited
1
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
2025
Cited
0
S2MNet: Speckle-To-Mesh Net for Three-Dimensional Cardiac Morphology Reconstruction via Echocardiogram
2025
Cited
0
Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions
2025
Cited
0
Co-authors
4 total
Shushan Wu
University of North Carolina at Chapel Hill
Tianhao Huang
University of Virginia
Lijie Hu
Assistant Professor, MBZUAI
Di Wang
King Abdullah University of Science and Technology
