Research
Robust Context-Aware Detection of Malicious Instructions in Text
We propose CAD, a defense that detects malicious instructions in text seen by LLM agents. CAD reads each sentence with the user query and surrounding context, then uses adversarial training to stay reliable under indirect prompt injection attacks.
Language Use in Indian Municipal Politics
We study how Indian municipal corporators change language as they move between voters and government offices. Using 230+ interviews, I built an AI-assisted pipeline that turns qualitative transcripts into structured language-use variables. The project shows that political speech is practical judgment, shaped by who is listening and what the situation demands.
Acting Out Who I Am: Will the Ethnic Identity of Minorities Die Out in Modernization?
I study how tourism changes minority identity in Guizhou. The paper argues that modernization does not erase identity in one uniform way. People respond differently depending on who controls cultural display and who benefits from tourism.