Summary of Evaluating the Performance Of Chatgpt For Spam Email Detection, by Shijing Si et al.
Evaluating the Performance of ChatGPT for Spam Email Detection
by Shijing Si, Yuwei Wu, Le Tang, Yugui Zhang, Jedrek Wosik, Qinliang Su
First submitted to arxiv on: 23 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
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 study evaluates the capabilities of ChatGPT, a large language model, in identifying spam emails in both English and Chinese datasets. The researchers employ in-context learning, which requires a prompt instruction with or without demonstrations, to detect spam emails. They also compare the performance of ChatGPT with five popular benchmark methods, including naive Bayes, support vector machines (SVM), logistic regression (LR), feedforward dense neural networks (DNN), and BERT classifiers. The results show that while ChatGPT performs well on the low-resourced Chinese dataset, it is significantly outperformed by deep supervised learning methods in the large English dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how good a big language model called ChatGPT is at finding spam emails in emails written in two different languages. They test ChatGPT by giving it instructions and examples of what to look for, and they compare its results with other ways of doing it that are commonly used. The results show that ChatGPT does well on small datasets but not as well on bigger ones. This is important because it could be a way to help people find spam emails more easily. |
Keywords
* Artificial intelligence * Bert * Language model * Large language model * Logistic regression * Naive bayes * Prompt * Supervised
