What is it about?
Advanced language models can now paraphrase text so well that it's hard to tell if a document was written by a human or a machine. This poses a challenge for maintaining academic honesty. To help solve this, we've created a new testing standard (benchmark) that includes articles rewritten by these sophisticated models. Our work provides researchers with a valuable resource: a large set of both original and machine-paraphrased texts, analysis on how these texts differ, and experiments to see how well current systems can detect paraphrasing. By making this information public, we aim to encourage further development of tools that can identify machine-generated text in academic settings.
Featured Image
Photo by National Cancer Institute on Unsplash
Read the Original
This page is a summary of: Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection, September 2021, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/jcdl52503.2021.00065.
You can read the full text:
Contributors
The following have contributed to this page
