About me
Ph.D. candidate in Artificial Intelligence specializing in Natural Language Processing. Research focuses on investigating and mitigating the effects of various biases within AI systems, with particular emphasis on detecting and reducing bias in Large Language Model-based applications. Current research interests include examining the impact of societal biases on medical diagnosis in healthcare AI systems.
Research Interests
- Robust AI: Developing AI systems that perform reliably across diverse and challenging environments
- Multi-Agent Systems: Investigating collaborative AI agents for complex decision-making tasks
- Bias Mitigation: Understanding and addressing societal biases in large language models
- Explainable AI: Creating transparent and interpretable AI systems for critical applications
- AI Safety in NLP: Ensuring safe deployment of language models in real-world scenarios
Research Projects
- Robust Machine Learning for Low-Quality and Heterogeneous Text Data Environments
- Understanding and Mitigating Societal Biases Embedded in Large Language Models
- Safe and Explainable AI Systems for Content Safety and Moderation
News
- 2025: Paper accepted at Machine Learning for Healthcare (MLHC) 2025
- 2024: Presented at Public Good Convergence Forum on LLMs and Human Collaboration
- 2023: Paper published at EACL 2023 (Findings)
Background
Completed dual degrees in Sociology and Applied Artificial Intelligence at Ajou University, providing a unique interdisciplinary perspective on the societal implications of AI technologies.