Fact-Enhanced Synthetic News Generation


  • Kai Shu Illinois Institute of Technology, Chicago, IL, USA
  • Yichuan Li Worcester Polytechnic Institute, Worcester, MA, USA
  • Kaize Ding Arizona State University, Tempe, AZ, USA
  • Huan Liu Arizona State University, Tempe, AZ, USA




Stylistic Analysis & Text Mining, Language Models


The advanced text generation methods have witnessed great success in text summarization, language translation, and synthetic news generation. However, these techniques can be abused to generate disinformation and fake news. To better understand the potential threats of synthetic news, we develop a novel generation method FACTGEN to generate high-quality news content. The majority of existing text generation methods either afford limited supplementary information or lose consistency between the input and output which makes the synthetic news less trustworthy. To address these issues, FACTGEN retrieves external facts to enrich the output and reconstructs the input claim from the generated content to improve the consistency among the input and the output. Experiment results on real-world datasets demonstrate that the generated news contents of FACTGEN are consistent and contain rich facts. We also discuss an effective defending technique to identify these synthetic news pieces if FACTGEN was used to generate fake news.




How to Cite

Shu, K., Li, Y., Ding, K., & Liu, H. (2021). Fact-Enhanced Synthetic News Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13825-13833. https://doi.org/10.1609/aaai.v35i15.17629



AAAI Technical Track on Speech and Natural Language Processing II