About Me

I am a PhD candidate in the Information Systems and Cyber Security Department at the University of Texas at San Antonio (UTSA), advised by Dr. Anthony Rios. My research focuses on developing fair and equitable AI systems to enhance automated decision-making in biomedical and social domains. By incorporating Social Determinants of Health (SDOH), I aim to create AI solutions that understand and address the diverse needs and experiences of individuals.

🔍 Research Interests

I address real-world challenges in healthcare and public health through three main areas:

1. Personalized Healthcare with AI

I leverage Natural Language Processing (NLP) to analyze unstructured data from Electronic Health Records (EHRs), such as doctors’ notes. This process extracts critical Social Determinants of Health (SDOH) like job status, living conditions, education, and treatment schedules. By organizing this data, we enable healthcare providers to develop personalized care plans tailored to each patient’s unique needs, leading to better health outcomes and more informed decisions.

2. Public Health Insights from Social Media

Social media significantly influences public perceptions and behaviors related to health. I analyze social media data to identify how people interpret news headlines and health information. For example, my research found that media often portrays female cyclists as more vulnerable or at fault than males. This bias can discourage women from cycling and hinder public health efforts to promote cycling as a healthy activity. Understanding these patterns helps in creating strategies for accurate and fair media coverage, ultimately supporting better public health initiatives.

3. Using Storytelling to Speculate on the Unintended Harms of AI Solutions

Inspired by Netflix’s Black Mirror, which shows how technology can unintentionally cause harm despite good intentions, this project uses Human-AI Interactive Storytelling to explore the risks of AI tools in healthcare. By simulating real-world scenarios with clinical decision support systems using large language models (LLMs), we help AI developers and healthcare administrators understand how these tools might fail and cause harm, such as patients getting seriously ill or dying, before they are developed or deployed.

📚 Publications

• Bike Frames: Understanding the Implicit Portrayal of Cyclists in the News
  Xingmeng Zhao, Xavier Walton, Suhana Shrestha, Anthony Rios.
  Forthcoming in: Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2025.

• Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations
  James Ford, Xingmeng Zhao, Dan Schumacher, and Anthony Rios.
  Forthcoming in: Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025).

• A Comprehensive Study of Gender Bias in Chemical Named Entity Recognition Models
  Xingmeng Zhao, Ali Niazi, Anthony Rios.
  Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024.

• Translating Natural Language Specifications into Access Control Policies by Leveraging Large Language Models
  Sherifdeen Lawal, Xingmeng Zhao, Anthony Rios, Ram Krishnan, and David Ferraiolo.
  Forthcoming in: IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications.

• UTSA-NLP at ChemoTimelines 2024: Evaluating Instruction-Tuned Language Models for Temporal Relation Extraction
  Xingmeng Zhao and Anthony Rios.
  Proceedings of ClinicalNLP Workshop at NAACL 2024.

• Improving Expert Radiology Report Summarization by Prompting Large Language Models with a Layperson Summary
  Xingmeng Zhao, Tongnian Wang, Anthony Rios.
  arXiv preprint arXiv:2406.14500, 2024.

• A Marker-based Neural Network System for Extracting Social Determinants of Health
  Xingmeng Zhao, Anthony Rios.
  Journal of the American Medical Informatics Association, 2023. d

• UTSA-NLP at RadSum23: Multi-modal Retrieval-Based Chest X-Ray Report Summarization
  Tongnian Wang, Xingmeng Zhao, Anthony Rios.
  Proceedings of BioNLP Workshop at ACL, 2023.

• BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?
  Xingmeng Zhao, Tongnian Wang, Sheri Osborn, and Anthony Rios.
  Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning (CoNLL) at EMNLP 2023.

• UTSA NLP at SemEval-2022 Task 4: An Exploration of Simple Ensembles of Transformers, Convolutional, and Recurrent Neural Networks
  Xingmeng Zhao, Anthony Rios.
  Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval), 2022.

• Turning Stocks into Memes: A Dataset for Understanding How Social Communities Can Drive Wall Street
  Richard Alvarez, Paras Bhatt, Xingmeng Zhao, Anthony Rios.
  Proceedings of the International AAAI Conference on Web and Social Media, 2022.

👨‍🏫 Teaching Experience

• Instructor, IS 1413 Excel for Business Information Systems, Spring 2023
• Instructor, IS 2053 Programming Languages I with Scripting, Spring 2024
• Instructor, IS 1403 Business Info Systems Fluency, Fall 2024

📄 CV

Download my CV.

For the most up-to-date list of my publications, please visit my Google Scholar Profile.