Summary of Hidding the Ghostwriters: An Adversarial Evaluation Of Ai-generated Student Essay Detection, by Xinlin Peng et al.
Hidding the Ghostwriters: An Adversarial Evaluation of AI-Generated Student Essay Detection
by Xinlin Peng, Ying Zhou, Ben He, Le Sun, Yingfei Sun
First submitted to arxiv on: 1 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles the challenge of detecting AI-generated student essays, particularly those that are designed to evade existing detectors. The authors propose AIG-ASAP, a dataset of AI-generated student essays with various perturbations to test the effectiveness of current detectors. Empirical experiments reveal that these detectors can be easily circumvented using simple automatic attacks, highlighting the need for more robust methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AI-generated student essays are becoming increasingly common in educational settings, but they also pose risks like plagiarism and the dissemination of fake news. To combat this issue, researchers have developed detectors to identify AI-generated content. However, these detectors have not been tested against adversarial perturbations specifically designed for student essay writing. This paper aims to fill this gap by creating AIG-ASAP, a dataset that simulates real-life scenarios and assesses the performance of current detectors. |
