Graph-enhanced Large Language Models in Asynchronous Plan Reasoning

Code and dataset repo for ICML-2024 paper Graph-enhanced Large Language Models in Asynchronous Plan Reasoning.

Naturalistic datasets used in the paper is in the folder data

You can use the code to generate naturalistic data in folder data_gen

The code for the benchmarking experiment is in folder benchmark_llm

The code and data for prototypical experiment can be found in prototypical

You can also see a quick preview of our recent train/test-split version of this dataset on huggingface.

Cite our paper

If you find this repo useful, please cite our paper as

@inproceedings{lingraph,
  title={Graph-enhanced Large Language Models in Asynchronous Plan Reasoning},
  author={Lin, Fangru and La Malfa, Emanuele and Hofmann, Valentin and Yang, Elle Michelle and Cohn, Anthony G and Pierrehumbert, Janet B},
  booktitle={Forty-first International Conference on Machine Learning}
}