Summary of Vietnamese Ai Generated Text Detection, by Quang-dan Tran et al.
Vietnamese AI Generated Text Detection
by Quang-Dan Tran, Van-Quan Nguyen, Quang-Huy Pham, K. B. Thang Nguyen, Trong-Hop Do
First submitted to arxiv on: 6 May 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 A novel dataset, ViDetect, is presented to address the growing concern of distinguishing between human-written and AI-generated text content. The dataset consists of 6,800 Vietnamese essay samples, with 3,400 authored by humans and the remaining 3,400 generated by Large Language Models (LLMs). To evaluate the effectiveness of various methods in detecting AI-generated text, state-of-the-art models like ViT5, BartPho, PhoBERT, mDeberta V3, and mBERT are employed. The results demonstrate the adaptability and effectiveness of different approaches in the Vietnamese language context, contributing to the growing body of research on AI-generated text detection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, a new dataset is created to help us tell apart human-written and AI-generated texts. This dataset has 6,800 examples of Vietnamese essays, with half written by humans and the other half generated by Large Language Models (LLMs). To see which methods work best for detecting AI-generated text, we used powerful models like ViT5, BartPho, PhoBERT, mDeberta V3, and mBERT. The results show that different approaches can be effective in the Vietnamese language. |
