MohammadHossein Rezaei

Email: mhrezaei@arizona.edu

I am a third-year undergraduate student at the University of Arizona UArizona majoring in Computer Science. I am a member of the Computational Language Understanding (CLU) Lab CLU lab advised by Dr. Eduardo Blanco. Previously, I was a research intern at Stanford University advised by Dr. Diyi Yang in the SALT Lab SALT . I am also a part of the Open Social World OSW group. I have worked on various projects in natural language processing and machine learning such as negation understanding, multilingual QA, and physical social norm understanding. Currently, I am working on projects related to commonsense reasoning and natural language understanding.

Outside research, I am a Course Coordinator (Head TA) for the CSc 144: Discrete Math for CS I course offered by the computer science department. I also serve as a Peer Mentor and a CS Ambassador for the department to help incoming students and promote computer science education. I am honored to have been awarded the Iranian Scholarship Foundation (ISF) undergraduate scholarship. In my free time, I enjoy playing the piano, listening to music, and hiking.

news

Apr 01, 2025	I will be joining Scale AI as a Research Intern in the summer of 2025.
Mar 03, 2025	Check out our recent preprint on EgoNormia: Benchmarking Physical Social Norm Understanding.
Jan 22, 2025	My paper, Making Language Models Robust Against Negation, has been accepted to NAACL 2025. See you in Albuquerque!
Aug 20, 2024	I participated in the LINXS Summer Research Program at Stanford University in the summer of 2024 as an undergraduate visiting research intern. I was advised by Dr. Diyi Yang in the SALT Lab.
May 16, 2024	My paper, Paraphrasing in Affirmative Terms Improves Negation Understanding, has been accepted to ACL 2024.

selected publications

EgoNormia

EgoNormia: Benchmarking Physical Social Norm Understanding

MohammadHossein Rezaei^*, Yicheng Fu^*, Phil Cuvin^*, Caleb Ziems, Yanzhe Zhang, Hao Zhu, and Diyi Yang

2025

arXiv Bib PDF Code Website

@misc{rezaei2025egonormiabenchmarkingphysicalsocial,
  title = {EgoNormia: Benchmarking Physical Social Norm Understanding},
  author = {Rezaei, MohammadHossein and Fu, Yicheng and Cuvin, Phil and Ziems, Caleb and Zhang, Yanzhe and Zhu, Hao and Yang, Diyi},
  year = {2025},
  eprint = {2502.20490},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}

NAACL
Making Language Models Robust Against Negation

MohammadHossein Rezaei, and Eduardo Blanco

In Proceedings of the 2025 Conference of the Nations of America Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Apr 2025

Abs arXiv Bib PDF

Negation has been a long-standing challenge for language models. Previous studies have shown that they struggle with negation in many natural language understanding tasks. In this work, we propose a self-supervised method to make language models more robust against negation. We introduce a novel task, Next Sentence Polarity Prediction (NSPP), and a variation of the Next Sentence Prediction (NSP) task. We show that RoBERTa and BERT further pre-trained on our tasks outperform the off-the-shelf transformer models on eight negation-related benchmarks. Most notably, the pretrainings yield between 1.8% and 9.1% improvement on CondaQA, a large question-answering corpus requiring reasoning over negation.
@inproceedings{rezaei-blanco-2025-making, title = {Making Language Models Robust Against Negation}, author = {Rezaei, MohammadHossein and Blanco, Eduardo}, booktitle = {Proceedings of the 2025 Conference of the Nations of America Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)}, month = apr, year = {2025}, address = {Albuquerque, New Mexico, USA}, url = {https://arxiv.org/abs/2502.07717}, notes = {To appear} }
ACL
Paraphrasing in Affirmative Terms Improves Negation Understanding

MohammadHossein Rezaei, and Eduardo Blanco

In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Aug 2024

Abs DOI arXiv Bib PDF Poster Slides

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks.
@inproceedings{rezaei-blanco-2024-paraphrasing, title = {Paraphrasing in Affirmative Terms Improves Negation Understanding}, author = {Rezaei, MohammadHossein and Blanco, Eduardo}, editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek}, booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, month = aug, year = {2024}, address = {Bangkok, Thailand}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2024.acl-short.55/}, doi = {10.18653/v1/2024.acl-short.55}, pages = {602--615}, }