Abolfazl Ansari

PhD Student

Pennsylvania State University

PA 16802, USA

I am a PhD student in Information Science and Technology at Pennsylvania State University, where I focus on research in Large Language Models, Vision-Language Models, and AI for Science.

My research interests span various areas of computational science, with particular emphasis on the applications and methodologies of LLMs and VLMs for scientific discovery and reasoning. I am delighted to work with brilliant minds in our community during my PhD.

Feel free to explore my publications, projects, and repositories to learn more about my work. You can also check out my teaching experience and materials. so ar

publications

Echoes of Automation: The Increasing Use of LLMs in Newsmaking

Abolfazl Ansari, Delvin Ce Zhang, Nafis Irtiza Tripto, and Dongwon Lee

arXiv preprintarXiv:2508.06445. To appear in SBP-BRiMS 2025 and Springer-Nature LNCS series , Aug 2025

18th International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation, Carnegie Mellon University

Abs DOI Bib HTML PDF

The rapid rise of Generative AI (GenAI), particularly LLMs, poses concerns for journalistic integrity and authorship. This study examines AI-generated content across over 40,000 news articles from major, local, and college news media, in various media formats. Using three advanced AI-text detectors (e.g., Binoculars, Fast-Detect GPT, and GPTZero), we find substantial increase of GenAI use in recent years, especially in local and college news. Sentence-level analysis reveals LLMs are often used in the introduction of news, while conclusions usually written manually. Linguistic analysis shows GenAI boosts word richness and readability but lowers formality, leading to more uniform writing styles, particularly in local media.
@article{ansari2025echoes, title = {Echoes of Automation: The Increasing Use of LLMs in Newsmaking}, author = {Ansari, Abolfazl and Zhang, Delvin Ce and Tripto, Nafis Irtiza and Lee, Dongwon}, journal = {arXiv preprint}, year = {2025}, month = aug, pages = {1--20}, publisher = {arXiv}, doi = {10.48550/arXiv.2508.06445}, url = {https://arxiv.org/abs/2508.06445}, note = {18th International Conference on Social Computing, Behavioral-Cultural Modeling, \& Prediction and Behavior Representation in Modeling and Simulation, Carnegie Mellon University} }