Skip to content

Train transformers on synthetic graph search problems to measure their scaling behavior and to do mechanistic analysis.

Notifications You must be signed in to change notification settings

asaparov/learning_to_search

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This repo contains code to perform the experiments and analysis in our paper: Transformers Struggle to Learn to Search

If you use this code in your work, please cite:

@inproceedings{
  TransformersStruggleToSearch,
  title={Transformers Struggle to Learn to Search},
  author={Abulhair Saparov and Srushti Pawar and Shreyas Pimpalgaonkar and Nitish Joshi and Richard Yuanzhe Pang and Vishakh Padmakumar and Seyed Mehran Kazemi and Najoung Kim and He He},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025},
  url={https://openreview.net/forum?id=qFVVBzXxR2V}
}

About

Train transformers on synthetic graph search problems to measure their scaling behavior and to do mechanistic analysis.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •