publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2025
-
Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis2025Accepted at AAAI 2026 XAI4Science Workshop -
RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation2025Accepted at NeurIPS 2025 LLM Evaluation Workshop Poster -
Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data2025Accepted at 2026 AAAI Workshop on Shaping Responsible Synthetic Data in the Era of Foundation Models