About me

Hey! I’m Liam, a fourth-year PhD student at the University of Pennsylvania, with the Penn NLP group. I am advised by Professor Chris Callison-Burch.

My research focuses on human and automated detection of AI-generated content. In particular, I am interested in the technical limitations and societal ramifications of detection tools and how we might deploy AI detectors with minimal harm. My work has been featured by CNN, ABC News, and Vice as well as in a testimony to the U.S. Congress.

My co-authors and I maintain the Real or Fake Text website where people can test how well they can detect generated text. We also recently released the RAID Benchmark the largest and most challenging dataset for comparing generated text detectors.

My previous work has included:

  • Customizing Machine Translation systems for Cross-Lingual Question Answering
  • Automatic Question Generation for “Smart Textbooks”
  • Developing low latency End-to-End Speech Translation

Outside of academia, I like to play chess, run, and study foreign languages. Feel free to reach out if you want to chat about my research or the PhD application process!

This semester (Fall 2024) I am organizing the weekly Penn Computational Linguistics Lunch (CLunch) Seminar and the Penn Statistical NLP Reading Group. Please reach out if you are a current Penn student and are interested in joining!