- Conduct research on LLM-based text simplification, focusing on handling numeric expression (e.g., dates, percentages, words)
- Perform EDA on the 300-article Newsela corpus using Python, pandas, and nltk
- Built data pipelines for text cleaning, feature extraction, and corpus refinement to support large-scale analysis
- Co-author on an accepted paper to be presented at AIME-Con 2025 (AI in Measurement and Education Conference)