Summary of Hatetinyllm : Hate Speech Detection Using Tiny Large Language Models, by Tanmay Sen et al.
HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models
by Tanmay Sen, Ansuman Das, Mrinmay Sen
First submitted to arxiv on: 26 Apr 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 introduces HateTinyLLM, a novel framework for efficient hate speech detection based on fine-tuned decoder-only tiny large language models (tinyLLMs). By exploring various tiny LLMs and fine-tuning them using LoRA and adapter methods, the authors demonstrate that their approach outperforms the pre-trained mixtral-7b model by a significant margin. The study’s experimental findings show that all LoRA-based fine-tuned models achieved over 80% accuracy. This paper contributes to the development of automated hate speech detection methods, particularly in the context of social media platforms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Hate speech is when someone says something mean or hurtful about another person or group because of who they are. For example, it might be a racist joke or a mean comment on social media. To help stop this kind of behavior online, researchers have been working on ways to detect hate speech using computers. One new way to do this is with tiny large language models, which are special kinds of artificial intelligence that can understand and generate text. In this study, scientists created a new method called HateTinyLLM that uses these tiny language models to detect hate speech. They tested their approach and found it works really well, achieving over 80% accuracy. |
Keywords
» Artificial intelligence » Decoder » Fine tuning » Lora
