Detecting Generated Scientific Papers using an Ensemble of Transformer Models
This work addresses the detection of AI-generated scientific papers, which is an incremental improvement in a specific domain.
The paper tackled the problem of automatically detecting generated scientific papers by developing an ensemble of transformer models, achieving a 99.24% F1-score and placing third in the DAGPap22 shared task.
The paper describes neural models developed for the DAGPap22 shared task hosted at the Third Workshop on Scholarly Document Processing. This shared task targets the automatic detection of generated scientific papers. Our work focuses on comparing different transformer-based models as well as using additional datasets and techniques to deal with imbalanced classes. As a final submission, we utilized an ensemble of SciBERT, RoBERTa, and DeBERTa fine-tuned using random oversampling technique. Our model achieved 99.24% in terms of F1-score. The official evaluation results have put our system at the third place.