About

I’m a final-year PhD student at the Department of Computer and Information Science, University of Pennsylvania, advised by Prof. Dan Roth.

My research spans natural language processing and broader artificial intelligence. Recently, I’m particularly interested in studying different types of conflicts that emerge in modern AI systems, including:

• Hallucinations, factuality and alignment — model generations that are non-factual, toxic, or unsubstantiated/contradictory to the contexts [Long-Context Hallucination, DeeptraceReward]
• Retrieval, knowledge conflicts, and reasoning — How can LLMs reason through conflicting knowledge from different sources (contextual/parametric knowledge)? [ConflictScore, Conflicting QA]
• Perspectives and biases — conflicts across different perspectives and opinions [Multi-Perspective Search, MultiOpEd, News Framing]

I’m passionate about building trustworthy AI systems and working on AI safety in general. Some of my other ongoing projects include:

• FloodRAG — can AI search survive a flood of machine-generated misinformation? Measuring how much fake web content it takes to make production RAG systems assert falsehoods
• DeepFake Video Detection

Some of my other past projects include:

• Open Source Project (Core Contributor) - Distilled Generative Text Embedding Model
• Framing Bias Detection
• RL training code models with retrieval
• Representation Learning for Authorship Representation