Detecting Machine-Generated Long-Form Content with Latent-Space Variables

Detecting Machine-Generated Long-Form Content with Latent-Space Variables

Yufei Tian, Zeyu Pan, and Nanyun Peng, in Proceedings of the Findings of ACL at The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2024.

Download the full text

Abstract

We propose a robust method to detect machine-generated long-form text by incorporating abstract elements as key deciding factors, leading to a 31% improvement over existing baselines.

Bib Entry

@inproceedings{tian2024detecting,
  author = {Tian, Yufei and Pan, Zeyu and Peng, Nanyun},
  title = {Detecting Machine-Generated Long-Form Content with Latent-Space Variables},
  booktitle = {Proceedings of the Findings of ACL at The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings)},
  year = {2024}
}

Related Publications

1. Detecting Machine-Generated Long-Form Content with Latent-Space Variables

   Yufei Tian, Zeyu Pan, and Nanyun Peng, in Proceedings of the Findings of ACL at The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2024.
   Full Text Abstract BibTeX Details

   We propose a robust method to detect machine-generated long-form text by incorporating abstract elements as key deciding factors, leading to a 31% improvement over existing baselines.

   @inproceedings{tian2024detecting,
     author = {Tian, Yufei and Pan, Zeyu and Peng, Nanyun},
     title = {Detecting Machine-Generated Long-Form Content with Latent-Space Variables},
     booktitle = {Proceedings of the Findings of ACL at The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings)},
     year = {2024}
   }
   

   Details