Skip to content

utahnlp/logic_as_loss_with_transformers

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

68 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Role of Transformer Architecture in the Logic-as-Loss Framework

Official Code and Data repository of our ECML-PKDD 2025 paper: The Role of Transformer Architecture in the Logic-as-Loss Framework.

This repository contains the code and data for our experiments on two tasks—Collinearity and Latin square-type puzzle reasoning—as well as the Appendix document.

  • Collinearity – code and data for geometric reasoning experiments.
  • Puzzles – code and data for Futoshiki and Sudoku experiments.

To run the code, create a conda environment with python3.10:

conda create --name py310 python=3.10

and install the requirements:

conda activate py310
conda install --file requirements.txt
pip install -r requirements.txt

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published