KID-Review: Knowledge-Guided Scientific Review Generation with Oracle Pre-training


  • Weizhe Yuan Carnegie Mellon University
  • Pengfei Liu Carnegie Mellon University



Speech & Natural Language Processing (SNLP)


The surge in the number of scientific submissions has brought challenges to the work of peer review. In this paper, as a first step, we explore the possibility of designing an automated system, which is not meant to replace humans, but rather providing a first-pass draft for a machine-assisted human review process. Specifically, we present an end-to-end knowledge-guided review generation framework for scientific papers grounded in cognitive psychology research that a better understanding of text requires different types of knowledge. In practice, we found that this seemingly intuitive idea suffered from training difficulties. In order to solve this problem, we put forward an oracle pre-training strategy, which can not only make the Kid-Review better educated but also make the generated review cover more aspects. Experimentally, we perform a comprehensive evaluation (human and automatic) from different perspectives. Empirical results have shown the effectiveness of different types of knowledge as well as oracle pre-training. We make all code, relevant dataset available: as well as the Kid-Review system:




How to Cite

Yuan, W., & Liu, P. (2022). KID-Review: Knowledge-Guided Scientific Review Generation with Oracle Pre-training. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11639-11647.



AAAI Technical Track on Speech and Natural Language Processing