Symbolic Working Memory Enhances Language Models for Complex Rule Application [[Paper]](https://arxiv.org/abs/2408.13654)

August 27, 2024 ยท View on GitHub

Illustration of Logic Scaffolding

This repository hosts the codes and data of our Symbolic Working Memory Enhanced Rule Application Framework.

Running neurosymbolic rule application

cd Src
run_scripts.sh

Before running, you need to set your API key for OpenAI in run_scripts.sh.

Authors and Citation

This study was authored by Siyuan Wang, Zhongyu Wei, Yejin Choi and Xiang Ren. We encourage the use of our code and data in your research and kindly request citation of our paper as follows:

@misc{wang2024symbolicworkingmemoryenhances,
      title={Symbolic Working Memory Enhances Language Models for Complex Rule Application}, 
      author={Siyuan Wang and Zhongyu Wei and Yejin Choi and Xiang Ren},
      year={2024},
      eprint={2408.13654},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2408.13654}, 
}