Welcome

My name is Catherine Arnett. I’m an NLP Researcher at EleutherAI. I am interested in cross-lingual and multilingual NLP. I received PhD in Linguistics with a specialization in Computational Social Science at UC San Diego.

To contact me, you can email me at catherine [dot] arnett [at] gmail [dot] com or find me on 🦋 BlueSky or Twitter.

Other links:

HuggingFace GitHub Google Scholar Semantic Scholar Orcid

News

• Our new benchmark, Global PIQA, is out in collaboration with over 300 authors. See the preprint or use the dataset now!
• I have a new blog post out called “There is no such thing as a tokenizer-free lunch”
• My paper with Tyler Chang, Stella Biderman, and Ben Bergen got accepted to NeurIPS! The preprint is out now!
• Sander Land and my paper, BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization, won Best Paper at the first Tokenization Workshop at ICML 2025! 🏆