BGE-SparseCL-msmarco

This repository contains the SparseCL model based on BAAI/bge-base-en-v1.5 and trained on the msmarco dataset.

SparseCL is designed for contradiction and counterargument retrieval.

For implementation and usage details, please see the SparseCL repository.

Citation

Please cite our paper if you use this model:

@inproceedings{xu2025contradiction,
  title={Contradiction Retrieval via Contrastive Learning with Sparsity},
  author={Xu, Haike and Lin, Zongyu and Chang, Kai-Wei and Sun, Yizhou and Indyk, Piotr},
  booktitle={International Conference on Machine Learning},
  year={2025}
}

License

MIT License.