About Me

I am a PhD student in the College of Information Sciences and Technology at Pennsylvania State University, where I contribute to the PrivaSeer Project under the supervision of Dr. Shomir Wilson and Dr. C. Lee Giles. My research lies at the intersection of Natural Language Processing (NLP), Responsible AI, and Human-Centred Computing.

🔍 Research Interests

My research aims to build tools and frameworks that promote transparency and safety for users in AI systems. Specific areas of interest include:

• User Privacy Right Analysis: I develop automated methods to audit the privacy policies and data-handling practices of websites and AI applications at scale. The goal is to uncover where these practices fall short of protecting user rights, holding technologies accountable to their promises.
• Tool Use Safety in LLM Agents and LLMs: As LLMs begin to take actions in the real world by using tools (like APIs), their potential for failure becomes more dangerous. I investigate the robustness of this tool-calling behavior, identifying critical failure points and developing safeguards to prevent unintended consequences.

🧪 Ongoing Projects

1. Sectoral Norm Discovery: Sectoral Analysis of Website Privacy Notices
   Uncovering sector-specific data practices to define normative patterns in privacy notices across industries.

2. Tool Selection Safety: Are LLMs Robust to Perturbations in Tool Descriptions?
   Evaluating how LLMs handle tool selection under adversarial prompt perturbations in in-context learning.

3. Large-Scale Exploration and Interpretation of Consumer-Oriented Legal Documents(COLDs)
   Application of LLMs and AI-agentic frameworks to eliminate obstacles toward enhancing consumers’ understanding of many legal documents that they are expected to agree on.

📚 Selected Publications

• SoAC and SoACer: A Sector-Based Corpus and LLM-Based Framework for Sectoral Website Classification
  Proceedings of the 25th ACM Symposium on Document Engineering (DocEng), 2025.

• The PrivaSeer Project: Large-Scale Resources for Analysis of Privacy Policy Text
  2025 Symposium on Usable Privacy and Security (SOUPS), USENIX.

• Generative Adversarial Learning with Negative Data Augmentation for Semi-Supervised Text Classification
  Proceedings of the 35th International Florida Artificial Intelligence Research Society Conference (FLAIRS-35), 2022.

For a full list of publications and academic contributions, please refer to Google Scholar.

🤝 Academic Service

• Reviewer, 5th Workshop on Trustworthy NLP (TrustNLP), NAACL 2025
• Graduate Student Panelist, IST 197: Introduction to Research, Penn State

💼 Past Affiliations

• NLP Lab – University of Ottawa: Worked on mitigating social bias in semi-supervised text classification.
• Canadian Heritage Research Internship: Conducted qualitative analysis on challenges faced by Canadian artists during COVID-19.
• Mila – Responsible AI and Human Rights Summer School(2023): Analyzing Challenges and Potentials in Responsible AI design.

🛠 Skills

• Languages: Python, Java, C++, SQL
• Frameworks: PyTorch, LangChain, AutoGen, TensorFlow, Scikit-learn,