Ashley (Ash) Lewis | PhD in Computational Linguistics

About Me

I graduated with my PhD in Computational Linguistics from The Ohio State University in May 2026, where I worked with Dr. Michael White. My research tackles one of the most critical challenges in modern AI: hallucination — when language models produce confident, fluent, but factually wrong outputs. I develop efficient, data-driven methods to detect and reduce hallucinations in dialogue systems, combining knowledge distillation, self-training, and novel evaluation frameworks built for real-world deployment. I am 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.

✨ Check out our new paper on hallucination detection, published in ACL 2026! VISTA: Verification In Sequential Turn-based Assessment

Research

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.

Hallucination Mitigation

Investigating scalable methods such as knowledge distillation, self-training, and synthetic data generation to improve factual accuracy and reliability of domain-specific dialogue models.

Evaluation Frameworks

Developing robust evaluation frameworks to better quantify hallucinations in dialogue settings, combining automated metrics with human evaluation for more effective assessment.

Efficient NLP

Optimizing training and evaluation methodologies to reduce misinformation while maintaining system efficiency, particularly for deployment in resource-constrained environments.

Publications

2026

VISTA: Verification In Sequential Turn-based Assessment

Ashley Lewis, Andrew Perrault, Eric Fosler-Lussier, Michael White

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)

ACL Anthology

2025

Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents

Ashley Lewis, Michael White, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang

GEM Workshop @ ACL 2025, Vienna, Austria

Paper

2024

Smoothed Embeddings for Robust Language Models

Ryo Hase, Md Rafi Ur Rashid, Ashley Lewis, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang

Safe Generative AI Workshop @ NeurIPS 2024

arXiv

OSU CompLing at the GEM'24 Data-to-Text Task

Alyssa Allen, Ashley Lewis, Yi-Chien Lin, Tomiris Kaumenova, Michael White

INLG 2024, Tokyo, Japan

Paper

Insights of a Usability Study for KBQA Interactive Semantic Parsing: Generation Yields Benefits over Templates but External Validity Remains Challenging

Ashley Lewis, Lingbo Mo, Marie-Catherine de Marneffe, Huan Sun, Michael White

HumEval Workshop @ LREC-COLING 2024, Torino, Italy

Paper

2023

Mitigating Harms of LLMs via Knowledge Distillation for a Virtual Museum Tour Guide

Ashley Lewis, Michael White

TLLM Workshop @ INLG 2023, Prague, Czech Republic

Paper

Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System

Lingbo Mo, Shijie Chen, Ziru Chen, Xiang Deng, Ashley Lewis, Sunit Singh, Samuel Stevens, Chang-You Tai, Zhen Wang, Xiang Yue, Tianshu Zhang, Yu Su, Huan Sun

SIGDIAL 2023, Prague, Czechia

Paper

2022

Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction

Lingbo Mo, Ashley Lewis, Huan Sun, Michael White

Findings of ACL 2022, Dublin, Ireland

Paper

INSPIRED: A Large-Scale Dataset and Simulation Framework for Exploring Interactive Learning in Knowledge-Based Question Answering

Lingbo Mo, Ashley Lewis, Huan Sun, Michael White

InterNLP Workshop 2022

Paper

Bootstrapping a User-Centered Task-Oriented Dialogue System

Shijie Chen, Ziru Chen, Xiang Deng, Ashley Lewis, Lingbo Mo, Samuel Stevens, Zhen Wang, Xiang Yue, Tianshu Zhang, Yu Su, Huan Sun

Alexa Prize TaskBot Challenge 2022

Paper

Invited Talks

I enjoy speaking about AI hallucination, dialogue systems, and making NLP research accessible. Available for speaking engagements — reach out via LinkedIn or .