Bart Mofe Rl Xsum

🚀 MoFE模型項目

本項目聚焦於文本摘要領域，旨在通過MoFE（Mixture of Factual Experts）方法控制抽象摘要中的幻覺問題，提升摘要的事實準確性。

📄 許可證

本項目採用BSD 3條款許可證。

📚 詳細文檔

引用信息

如果你使用了本項目的相關內容，請引用以下論文：

@article{DBLP:journals/corr/abs-2110-07166,
  author    = {Prafulla Kumar Choubey and
               Jesse Vig and
               Wenhao Liu and
               Nazneen Fatema Rajani},
  title     = {MoFE: Mixture of Factual Experts for Controlling Hallucinations in
               Abstractive Summarization},
  journal   = {CoRR},
  volume    = {abs/2110.07166},
  year      = {2021},
  url       = {https://arxiv.org/abs/2110.07166},
  eprinttype = {arXiv},
  eprint    = {2110.07166},
  timestamp = {Fri, 22 Oct 2021 13:33:09 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2110-07166.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

相關信息