Summary of Fine-tuning Pre-trained Language Models to Detect In-game Trash Talks, by Daniel Fesalbon et al.
Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks
by Daniel Fesalbon, Arvin De La Cruz, Marvin Mallari, Nelson Rodelas
First submitted to arxiv on: 19 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: 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 The paper explores the issue of toxic behavior and abuse among players in online games, including its impact on in-game performance and overall well-being. It also discusses the role of pre-trained language models in detecting and classifying such messages. The study employs BERT (Base-uncased), BERT (Large-uncased), and GPT-3 models to classify toxicity levels in DOTA 2 game chats, achieving state-of-the-art performance. This research demonstrates the potential of pre-trained language models for addressing online hate speech and toxic behavior. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study looks at how people behave badly while playing games online and how it affects them. It also talks about if special computer programs can help fix this problem by recognizing mean messages. The researchers took chat messages from a popular game, labeled them as not mean, a little mean, or very mean, and then tested some famous AI models to see if they could do better than humans at picking out the bad messages. This study shows that these special computer programs can be really good at helping solve this problem. |
Keywords
* Artificial intelligence * Bert * Gpt
