Probabilistic Conceptual Explainers
for Foundation Models

This repo contains the code and data for our PACE (ICML 2024 paper):

Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
Hengyi Wang, Shiwei Tan, Hao Wang
[Paper] [ICML Website]

and our VALC (EMNLP 2024 Findings paper):

Variational Language Concepts for Interpreting Foundation Language Models
[Paper] [ACL Website]

Probabilistic Conceptual Explainers (PACE) for Vision Transformers

Installation

conda env create -f environment_PACE.yml
conda activate PACE
cd src

Generate the Color Dataset

python generate_data.py

Finetune ViT for the Color Dataset

python main.py --train  --task Color --name ViT-base --num_epochs 5 --lr 1e-3 --require_grad

Train PACE for the Color Dataset

python main.py --train  --task Color --name ViT-PACE --num_epochs 1

Test PACE for the Color Dataset

python main.py  --task Color --name ViT-PACE --num_epochs 1

Probabilistic Conceptual Explainers (VALC) for Pretrained Language Models

Coming Soon!

Reference

@inproceedings{PACE,
  title={Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models},
  author={Hengyi Wang and
          Shiwei Tan and
          Hao Wang},
  booktitle={International Conference on Machine Learning},
  year={2024}
}

@inproceedings{VALC,
  title={Variational Language Concepts for Interpreting Foundation Language Models},
  author={Hengyi Wang and
          Shiwei Tan and
          Zhiqing Hong and 
          Desheng Zhang and
          Hao Wang},
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2024},
  year={2024}
}