Research Overview

My research focuses on trustworthy and knowledge-aware NLP, with particular interest in retrieval-augmented generation, computational semantics, and interpretable language models. I investigate robust and compositional approaches for biomedical AI by integrating neural language models with symbolic and retrieval-based reasoning frameworks. My work explores adversarial robustness, explainability, and contextual grounding in large language models for high-stakes applications such as scientific discovery, biomedical question answering, and evidence-based text generation.