Alexander Wettig

I'm a PhD student in the Princeton NLP group, advised by Danqi Chen, and affiliated with PLI. Previously, I graduated with a BA & MEng from the University of Cambridge, where I worked with Adrian Weller.

I am interested in improving our understanding of language models in terms of their training data, architecture and training objective.

Publications

(* indicates equal contribution)

• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
  Carlos E. Jimenez*, John Yang*, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, Karthik Narasimhan
  Pre-print 2023

• Adapting Language Models to Compress Contexts
  Alexis Chevalier*, Alexander Wettig*, Anirudh Ajith, Danqi Chen
  Pre-print 2023

• Learning Transformer Programs
  Dan Friedman, Alexander Wettig, Danqi Chen
  Pre-print 2023

• A Kernel-Based View of Language Model Fine-Tuning
  Sadhika Malladi, Alexander Wettig, Dingli Yu, Danqi Chen, Sanjeev Arora
  ICML 2023

• Should You Mask 15% in Masked Language Modeling?
  Alexander Wettig*, Tianyu Gao*, Zexuan Zhong, Danqi Chen
  Proceedings of EACL 2023

• Finding Dataset Shortcuts with Grammar Induction
  Dan Friedman, Alexander Wettig, Danqi Chen
  Proceedings of EMNLP 2022

• Phrase Retrieval Learns Passage Retrieval, Too
  Jinhyuk Lee, Alexander Wettig, Danqi Chen
  Proceedings of EMNLP 2021