VISTA Score: Verification In Sequential Turn-based Assessment
arXiv preprint (Under review)
PhD Candidate in Computational Linguistics
The Ohio State University
On the job market for 2025
I am a PhD candidate in Computational Linguistics at The Ohio State University, where I work with Dr. Michael White. My research focuses on mitigating hallucinations in dialogue systems through efficient, data-driven approaches. I am graduating in May 2025 and actively seeking opportunities in research and industry.
Prior to my PhD, I received my BA in English and BA in Linguistics from the University of Kentucky in 2013. Before starting grad school, I spent three years abroad teaching English—one year in Poland and two years in South Korea.
My international experience and background in linguistics inform my approach to NLP research, giving me a unique perspective on language understanding and human-AI interaction.
My research focuses on mitigating hallucinations in interactive dialogue systems through efficient, data-driven approaches, with the goal of enhancing the usability of AI-driven systems in resource-constrained environments.
Investigating scalable methods such as knowledge distillation, self-training, and synthetic data generation to improve factual accuracy and reliability of domain-specific dialogue models.
Developing robust evaluation frameworks to better quantify hallucinations in dialogue settings, combining automated metrics with human evaluation for more effective assessment.
Optimizing training and evaluation methodologies to reduce misinformation while maintaining system efficiency, particularly for deployment in resource-constrained environments.
arXiv preprint (Under review)
GEM Workshop @ ACL 2025, Vienna, Austria
Safe Generative AI Workshop @ NeurIPS 2024
INLG 2024, Tokyo, Japan
HumEval Workshop @ LREC-COLING 2024, Torino, Italy
TLLM Workshop @ INLG 2023, Prague, Czech Republic
SIGDIAL 2023, Prague, Czechia
Findings of ACL 2022, Dublin, Ireland
InterNLP Workshop 2022
Alexa Prize TaskBot Challenge 2022
I enjoy speaking about AI hallucination, dialogue systems, and making NLP research accessible. Available for speaking engagements — reach out via LinkedIn.
Tokyo, Japan
Hallucination in AI Dialogues: Detection and Mitigation
Introducing VISTA Score: Verification in Sequential Turn-Based Assessment
Hallucination in the Wild: A Field Guide for LLM Users
Spotting, Understanding, and Reducing AI Mistakes
A summary of my academic background, research experience, and achievements.
When I'm not researching NLP, I embroider. I'm available for commissions — check out more of my work on Instagram.
I'm always happy to chat about research, collaborations, job opportunities, or speaking engagements. The best way to reach me is via LinkedIn.