Scholar
Mengnan Du
Google Scholar ID: 0i-Js2gAAAAJ
Assistant Professor, New Jersey Institute of Technology
Explainability
Natural Language Processing
Trustworthy AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
8,423
H-index
35
i10-index
72
Publications
20
Co-authors
27
list available
Contact
No contact links provided.
Publications
44 items
Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
2026
Cited
0
FinAnchor: Aligned Multi-Model Representations for Financial Prediction
2026
Cited
0
AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling
2026
Cited
0
LLM Agents in Law: Taxonomy, Applications, and Challenges
arXiv.org · 2026
Cited
0
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
arXiv.org · 2026
Cited
0
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
2025
Cited
0
Rep2Text: Decoding Full Text from a Single LLM Token Representation
2025
Cited
0
KnowThyself: An Agentic Assistant for LLM Interpretability
2025
Cited
0
Load more
Resume (English only)
Co-authors
27 total
Fan Yang
Assistant Professor of Computer Science, Wake Forest University
Xia "Ben" Hu
Professor of Computer Science, Rice University
Ninghao Liu
Assistant Professor, University of Georgia
Na Zou
Assistant Professor, University of Houston
Co-author 5
Yongfeng Zhang
Professor of Computer Science, Rutgers University
Haofan Wang
Lovart AI, InstantX, Carnegie Mellon University
Guanchu Wang
Assistant Professor of Computer Science, University of North Carolina at Charlotte
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up