Detecting Hate Speech with GPT-3

By Ke-Li Chiu, Rohan Alexander. 2021

140 citations recorded by the source corpus.

Sophisticated language models such as OpenAI's GPT-3 can generate hateful text that targets marginalized groups. Given this capacity, we are interested in whether large language models can be used to identify hate speech and classify text as sexist or racist. We use GPT-3 to identify sexist and racist text passages with zero-, one-, and few-shot learning. We find that with zero- and one-shot learning, GPT-3 can identify sexist or racist text with an average accuracy between 55 per cent and 67 per cent, depending on the category of text and type of learning. With few-shot learning, the model's accuracy can be as high as 85 per cent. Large language models have a role to play in hate speech detection, and with further development they could eventually be used to counter hate speech.

Subfields: Artificial Intelligence, Large Language Models, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Luke S. Zettlemoyer
2. Jason Aaron Edward Weston
3. Graham Neubig
4. Hannaneh Hajishirzi
5. Mohit Bansal
6. Jie Tang
7. Kurt Shuster
8. Noah A. Smith

In Large Language Models

1. Luke S. Zettlemoyer
2. Jie Tang
3. Xiao Liu
4. Ming Ding
5. Myle Ott
6. Kurt Shuster
7. Naman Goyal
8. Mona T. Diab

In Natural Language Processing

1. Luke S. Zettlemoyer
2. Jason Aaron Edward Weston
3. Graham Neubig
4. Mohit Bansal
5. Hannaneh Hajishirzi
6. Yejin Choi
7. Kurt Shuster
8. Xian Li

Citations in the corpus

• OPT: Open Pre-trained Transformer Language Models (2022, methodology): “Using the ETHOS dataset provided in Mollas et al. (2020) and instrumented by Chiu and Alexander (2021), we measure the ability of OPT-175B to identify whether or not certain English statements are racist or sexist (or neither).”
• GLM-130B: An Open Bilingual Pre-trained Model (2022, methodology): “We adopt the ETHOS dataset originally proposed in (Mollas et al., 2020) to detect sexism and racism speech on zero-shot or few-shot datasets created by (Chiu & Alexander, 2021).”
• GPT-3 and InstructGPT: technological dystopianism, utopianism, and “Contextual” perspectives in AI ethics and industry (2022, background): “[4], Lucy and Bamman [9], Chiu and Alexander [37]), I will focus on the two issues of manipulation and bias.”