Grounding & knowledge
Evidence-grounded language models
I build retrieval, knowledge-graph, and multi-agent methods that connect model outputs to authoritative evidence—making high-stakes responses more factual, traceable, and robust.
Ph.D. Student · NLP & Large Language Models
I build trustworthy language models for high-stakes communication.
My research grounds LLMs in reliable evidence, adapts responses to the people reading them, and tests whether they remain factual, consistent, and useful.
University of North Texas
Denton, Texas
01 / Research focus
From capable language models to dependable ones.
I study how language models can communicate reliable information in high-stakes settings. Working with Dr. Lingzi Hong in the Human-Centered Computing Lab.
I connect evidence-grounded generation, human-adaptive responses, and rigorous evaluation to produce safer AI support for health misinformation and crisis communication.
- Trustworthy LLMs
- Knowledge Graphs & RAG
- Human-Centered AI
- Multi-Agent Systems
- LLM Evaluation
Research highlights
How I approach trustworthy, human-centered NLP.
People & interaction
Adaptive human–AI interaction
I study when an AI should ask, answer, adapt, or collaborate—using controllable generation, literacy-aware methods, and human feedback to fit the reader and the moment.
Measurement & reliability
Evaluation for high-stakes NLP
I design benchmarks, metrics, and human studies that test factuality, consistency, audience alignment, actionability, and situational awareness in health and crisis communication.
Selected work
Featured publications
2026
Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention ↗
A decision framework that learns when a health-misinformation intervention should ask for clarification and when it should answer directly.
2025
Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation →
Specialized agents retrieve, summarize, generate, and refine evidence-based counterspeech using static and dynamic sources.
Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL →
A RAG and reinforcement-learning framework for generating evidence-grounded counterspeech at the reader's health-literacy level.
Latest
Recent news
Ask or Answer accepted at EMNLP 2026
Our decision framework studies when a health-misinformation intervention should ask for clarification and when it should answer directly.
Read the paperThree systems at CLEF CheckThat! 2026
SciClaimSeekers, SourceMinds, and VeriFind addressed scientific-source retrieval, citation auditing, and numerical claim verification; VeriFind placed second in Task 2.
View 2026 publicationsStarted my Ph.D. at the University of North Texas
I began the Computer Science and Engineering program, focusing on trustworthy language systems for health and crisis communication.
View academic journeyCompleted my M.S. in Data Science
I graduated from the University of North Texas with a 4.00/4.00 GPA.
View educationCollaboration