Mengnan Du

Mengnan Du

Assistant Professor

New Jersey Institute of Technology


I am an assistant professor in the Department of Data Science, New Jersey Institute of Technology (NJIT), with a joint appointment in the Department of Computer Science. I lead the Trustworthy Machine Learning Research Lab (TMLR lab). Before that, I earned the Ph.D. in Computer Science from Texas A&M University, under supervision of Dr. Xia Hu. I have previously worked/interned with companies such as MSR, Adobe Research, and Intel. I also work closely with Dr. Ben Shneiderman of University of Maryland, and developed a website for Human-Centered AI.

My research interests lie within the extensive domain of trustworthy machine learning, with a particular emphasis on explainability, fairness, robustness, etc. Additionally, I am particularly intrigued by the intersection of trustworthy machine learning with large language models (LLMs). We summarize our recent efforts in trustworthy LLMs here.

I’m actively looking for strong and motivated students. If you are interested in working with me, please feel free to email me. Please check here for more details.


03/2024: One paper accepted by NAACL Findings 2024
02/2024: Two papers accepted by COLING 2024
02/2024: Check preprint about our position on LLM explainability
01/2024: Papers accepted by TPAMI, TAI and ICLR
01/2024: Check our preprint explaining how LLM CoT works
11/2023: Our survey paper on LLM Explainability gets accepted by ACM TIST
11/2023: Invited to serve as a Senior Program Committee Member for IJCAI-24
11/2023: One workshop proposal gets accepted by WWW 2024
09/2023: One paper accepted by NeurIPS 2023
09/2023: One paper accepted by NeurIPS 2023 Datasets and Benchmarks track
09/2023: Our workshop proposal on “Responsible Language Models” has been accepted by AAAI 2024
08/2023: Honored to receive an NSF IIS medium grant as NJIT PI
08/2023: Two papers accepted by CIKM 2023
07/2023: Invited to be a reviewer for Nature Communications
07/2023: One paper accepted by ECAI 2023
06/2023: Two papers accepted by ECML-PKDD 2023
05/2023: One paper on shortcut learning of large language models (LLMs) gets accepted by Communications of the ACM
05/2023: One paper on LLMs fairness accepted by ACL 2023
04/2023: Grateful to receive one NJIT Faculty Seed Grant Award
04/2023: One paper accepted by ICML 2023
04/2023: One paper accepted by IJCAI 2023
03/2023: Serving as Editorial Board Member of Journal of Information Analysis
01/2023: One paper on LLMs robustness accepted by EACL 2023
10/2022: Invited to serve on the Senior program committee at IJCAI 2023
10/2022: Invited to the TWEB Distinguished Reviewer Board
09/2022: Hosted MLNLP seminar on Trustworthy AI
08/2022: Invited to be a reviewer for Nature Machine Intelligence
05/2022: Invited to give a talk on GNN explainability at DataFun on June 25
05/2022: One paper accepted by KDD 2022
05/2022: One paper accepted by ICML 2022
01/2022: One paper accepted by ICLR 2022