Hadi Amiri

Assistant Professor Miner School of Computer & Information Sciences University of Massachusetts (UMass) Lowell Email: hadi@cs.uml.edu Web: cs.uml.edu/~hadi Lab: clu.cs.uml.edu/ CV

I direct the Computational Language Understanding (CLU) lab, where my students and I investigate some of the key problems in NLP and Trustworthy AI with applications in healthcare.

Prospective PhD students: if you are a motivated student and passionate about research, please see this page for current research opportunities.

Updates

Research

My research centers on strategies for controlling AI models and unlearning spurious, noisy and biased data from them. Below is a selection of my publications and the complete list can be found here.

• Tool Unlearning for Tool-Augmented LLMs
  Jiali Cheng, Hadi Amiri. In Proceedings of International Conference on Machine Learning (ICML’25).

• FairFlow: Mitigating Dataset Biases through Undecided Learning for Natural Language Understanding
  Jiali Cheng, Hadi Amiri. In Proceedings of The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP’24).

• HuCurl: Human-induced Curriculum Discovery
  Mohamed Elgaar, Hadi Amiri. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23).

• Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach
  Nidhi Vakil, Hadi Amiri. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23).

• Machine Learning of Patient Characteristics to Predict Admission Outcomes in the Undiagnosed Diseases Network
  Hadi Amiri, Issac S. Kohane. Journal of the American Medical Association (JAMA). 2021.

• Neural Self-Training through Spaced Repetition
  Hadi Amiri. The 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’19).

• Serial Recall Effects in Neural Language Modeling
  Hassan Hajipoor, Hadi Amiri, Maseud Rahgozar, Farhad Oroumchian. The 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’19).

• Spotting Spurious Data with Neural Networks
  Hadi Amiri, et al. The 2018 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’18).

• Repeat before Forgetting: Spaced Repetition for Efficient and Effective Training of Neural Networks
  Hadi Amiri, et al. The 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP’17).

• Target-dependent Churn Classification in Microblogs
  Hadi Amiri, Hal Daumé III. The 29th Conference of the Association for the Advancement of Artificial Intelligence (AAAI’15).

Teaching

• Social Computing

• Natural Language Processing

• Machine Learning

• Graph Machine Learning

Contact

• One University Avenue, 334 Dandeneau Hall, Lowell, MA 01854

• hadi@cs.uml.edu | hadi_amiri@uml.edu | @amirieb

• +1 (978) 934 3612