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

• Global PIQA is accepted to NeurIPS E&D! See the preprint or use the dataset now!
• My collaborators and I have five papers that will appear at EMNLP, including one oral! See my research page for preprints.
• New preprint: How Open Must Language Models be to Enable Reliable Scientific Inference?
• Our paper CommonLID has been accepted to ACL 2026!
• Our paper Weight Tying Biases Token Embeddings Towards the Output Space was accepted to Findings of ACL 2026!