Building reliable language models for high-stakes communication.
I am a Ph.D. student at the University of North Texas. I study how language models retrieve trustworthy evidence, adapt explanations to different readers, and communicate reliably in health and crisis settings.
Advised by Dr. Lingzi Hong · Human-Centered Computing Lab
Open to 2027 research internships in Applied Science, NLP, and Machine Learning.
Get in touch01 / SELECTED RESEARCH
Research on evidence-grounded NLP, audience-aware communication, and reliable AI in health and crisis settings.
Coordinating specialized agents and multiple evidence sources to generate and refine grounded corrections.
Runner-up · SIG-SM Social Media Research Competition
Choosing between clarification and a direct response; roughly 30% fewer dialogue turns than always-probing approaches.
Adapting evidence-grounded health corrections to readers with different literacy needs.
Finalist · SIG-SM Social Media Research Competition
02 / RESEARCH
Three connected questions guide my work: what evidence is needed, how to communicate it, and how to evaluate the result.
Explore all researchEvidence & grounding
Using retrieval, knowledge graphs, and collaborating agents to connect language generation with trustworthy sources.
People & interaction
Designing systems that know when to ask, answer, and adapt explanations to the needs of different readers.
Reliability & evaluation
Building benchmarks, metrics, and human studies for factuality, consistency, usefulness, and situational awareness.
04 / CONNECT
Interested in trustworthy NLP, human-centered AI, or potential collaborations? I would be happy to connect.