Jenna Russell

Welcome! I’m Jenna, a first-year Computer Science PhD student at the University of Maryland, College Park, where I am advised by Professor Mohit Iyyer. Prior to UMD, I spent a semester as a PhD student at University of Massachusetts Amherst, where I was also advised by Professor Iyyer. My current research interests include automatic text detection, understanding the differences in lexical patterns between LLM-generated and human-written text, and how humans can reliably use LLM generated texts.

Prior to joining UMass, I was a data scientist for Bank of America, doing applied research for Erica Conversational AI. I completed my B.S. at Cornell University, majoring in Statistics and Information Science, and grew up in nearby Rochester, New York.

Outside of my PhD, I spend my time lifting, running, and reading. I fit in somewhere between 70-100 books a year, mostly through audiobooks. Check out my Goodreads, which I update pretty much daily. I also have a 13-year old cat named Boo.

news

Apr 21, 2025	Forbes wrote about my work on human detection of AI, see the article here.
Jan 26, 2025	I’ve published my first paper, People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text.
Jan 11, 2025	We’ve moved to the CLIP Lab at UMD College Park.
Oct 06, 2024	I’m attending COLM this week.
Sep 02, 2024	I started my PhD at UMass Amherst!

selected publications

arXiv

People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text

Jenna Russell, Marzena Karpinska, and Mohit Iyyer

2025

Bib PDF Code

@article{russell_humandetectors25,
  title = {People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text},
  author = {Russell, Jenna and Karpinska, Marzena and Iyyer, Mohit},
  year = {2025},
  publisher = {arXiv},
  url = {https://arxiv.org/abs/2501.15654},
}

arXiv

One ruler to measure them all: Benchmarking multilingual long-context language models

Yekyung Kim, Jenna Russell, Marzena Karpinska, and 1 more author

2025

Bib PDF Code

@article{kim2025oneruler,
  title = {One ruler to measure them all: Benchmarking multilingual long-context language models},
  author = {Kim, Yekyung and Russell, Jenna and Karpinska, Marzena and Iyyer, Mohit},
  year = {2025},
  publisher = {arXiv},
  url = {https://arxiv.org/abs/2503.01996},
}