Zhengxiang Wang

I am a PhD candidate in Computational Linguistics at Stony Brook University, affiliated with Institute for Advanced Computational Science (IACS). I am fortunate to be advised by Dr. Owen Rambow.

Prior to coming to Stony Brook, I completed a bachelor's degree in Chinese Language and Literature from Hunan University, and a master's degree in Applied linguistics from University of Saskatchewan.

I am a lifelong learner at heart, and as a result my research interests have evolved over time. Currently, my work focuses on evaluating large (vision/audio/omni) language models from a human-centric perspective, spanning themes such as multi-step and agentic reasoning, human–AI interaction, personalization, multimodality, and post-training. I prioritize research grounded in real-world use cases and open-ended challenges, with an emphasis on scalable and interpretable evaluation methodologies.

I enjoy making new connections, so feel free to reach out to me for any reason and have a coffee chat!

News

Jan, 2026: Launched a new Blogs section on my website, featuring various essays I wrote between 2015 and 2019. I hope this will motivate me to write more going forward.
Aug, 2025: I started working for Amazon as an Applied Sciencist intern. I research in Large Audio Language Model for the Central Analytics and Research Science team under Alexa AI.
Aug, 2025: My first-authored paper LVLMs are Bad at Overhearing Human Referential Communication has been accepted to EMNLP 2025 (Main).
Aug, 2025: My first-authored paper Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors has been accepted to EMNLP 2025 (Findings).
May, 2025: I started working for Meta as a Software Engineer (Machine Learning) intern. Using Hack (PHP), I built an LVLM-based agentic workflow for trend detection, validation, magnitude labeling, and post content quality rating.
May, 2025: My first-authored paper LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing has been accepted to ACL 2025 (Main).
Feb, 2025: I advanced to PhD candidacy after passing my second qualifying paper.
Aug, 2024: I received the Junior Researcher Award from the Institute for Advanced Computational Science at Stony Brook University.
May, 2024: I started working for the Home Depot as a Data Scientist intern where I developed various LLM-based systems for topic modeling, classification, and validation.
June, 2023: I became a trainee for the Bias-NRT (National Science Foundation Research Traineeship) program at Stony Brook University,
Aug, 2022: I started my PhD in Computational Linguistics at Stony Brook University.

Research

For a full and up-to-date list of publications, please check my Google Scholar page.

Measuring Iterative Temporal Reasoning with Time Puzzles
Zhengxiang Wang, Zeyu Dong
Preprint, 2026

LVLMs and Humans Ground Differently in Referential Communication
Peter Zeng, Weiling Li, Amie J. Paige, Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras, Greg Zelinsky, Susan Brennan, Owen Rambow
Preprint, 2026

LVLMs are Bad at Overhearing Human Referential Communication
Zhengxiang Wang, Weiling Li, Panagiotis Kaliosis, Owen Rambow, Susan Brennan
EMNLP 2025 (Main)

Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors
Zhengxiang Wang*, Nafis Irtiza Tripto*, Solha Park, Zhenzhen Li, Jiawei Zhou
EMNLP 2025 (Findings)

LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing
Zhengxiang Wang, Veronika Makarova, Zhi Li, Jordan Kodner, Owen Rambow
ACL 2025 (Main)

Evaluating LLMs with Multiple Problems at once
Zhengxiang Wang, Jordan Kodner, Owen Rambow
GEM 2025

Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents
Zhengxiang Wang, Owen Rambow
NLP+CSS @ NAACL 2024

Learning Transductions and Alignments with RNN Seq2seq models
Zhengxiang Wang
ICGI 2023 | PMLR

Developing literature review writing skills through an online writing tutorial series: Corpus-based evidence
Zhi Li, Makarova Veronika, Zhengxiang Wang
Frontiers in Communication 2023

Random Text Perturbations Work, but not Always
Zhengxiang Wang
Eval4NLP @ AACL-IJCNLP 2022

Thirty-Two Years of IEEE VIS: Authors, Fields of Study and Citations
Hongtao Hao, Yumian Cui, Zhengxiang Wang, Yea-Seul Kim
IEEE Transactions on Visualization and Computer Graphics 2022

Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching
Zhengxiang Wang
ICNLSP 2022 | ACL Anthology

A macroscopic re-examination of language and gender: a corpus-based case study in the university classroom setting
Zhengxiang Wang
MA Thesis, University of Saskatchewan, 2021