Bart CaPE Xsum

🚀 摘要總結模型 - CaPE

CaPE是一種用於減少摘要總結中幻覺現象的模型，通過對比參數集成的方法提升總結的準確性和可靠性，適用於相關文本摘要任務。

📚 詳細文檔

引用信息

@misc{https://doi.org/10.48550/arxiv.2110.07166,
  doi = {10.48550/ARXIV.2110.07166},
  url = {https://arxiv.org/abs/2110.07166},
  author = {Choubey, Prafulla Kumar and Fabbri, Alexander R. and Vig, Jesse and Wu, Chien-Sheng and Liu, Wenhao and Rajani, Nazneen Fatema},
  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization},
  publisher = {arXiv},
  year = {2021},
  copyright = {Creative Commons Attribution 4.0 International}
}

模型信息

📄 許可證

本項目採用BSD 3條款許可證。