Summary of Assessing Large Language Models For Online Extremism Research: Identification, Explanation, and New Knowledge, by Beidi Dong et al.
Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge
by Beidi Dong, Jin R. Lee, Ziwei Zhu, Balassubramanian Srinivasan
First submitted to arxiv on: 29 Aug 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 The study evaluates the performance of two large language models, BERT and GPT, in detecting and classifying online domestic extremist posts. The researchers collected social media posts containing “far-right” and “far-left” ideological keywords and manually labeled them as extremist or non-extremist. They then trained the BERT model on different datasets sizes to assess its performance. Additionally, they compared the performance of GPT 3.5 and GPT 4 models using various prompts, finding that more detailed prompts generally yielded better results. The study concludes that large language models, specifically GPT, have significant potential for online extremism classification tasks, surpassing traditional BERT models in a zero-shot setting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special computer models to help find and stop bad ideas spreading online. These models are good at understanding what people write, and can be trained to recognize when someone is saying something extreme or violent. The researchers tested two of these models, called BERT and GPT, to see how well they could do this job. They found that one model, GPT, was really good at recognizing bad ideas, especially if the person using it wrote a clear description of what was wrong with the idea. This is important because there are many people spreading bad ideas online, and we need ways to stop them. |
Keywords
» Artificial intelligence » Bert » Classification » Gpt » Zero shot
