Chain of Explanation: New Prompting Method to Generate Quality Natural Language Explanation for Implicit Hate Speech

By Fan Huang, Haewoon Kwak, Jisun An. 2022

40 citations recorded by the source corpus.

Recent studies have exploited advanced generative language models to generate Natural Language Explanations (NLE) for why a certain text could be hateful. We propose the Chain of Explanation (CoE) Prompting method, using the heuristic words and target group, to generate high-quality NLE for implicit hate speech. We improved the BLUE score from 44.0 to 62.3 for NLE generation by providing accurate target information. We then evaluate the quality of generated NLE using various automatic metrics and human annotations of informativeness and clarity scores.

Subfields: Artificial Intelligence, Natural Language Processing, Prompting & Reasoning

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. Jisun An
2. Fan Huang
3. Haewoon Kwak
4. Hung-yi Lee
5. Cheng-Han Chiang

In Natural Language Processing

1. Jisun An
2. Fan Huang
3. Haewoon Kwak
4. Hung-yi Lee
5. Cheng-Han Chiang

Citations in the corpus

• Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech (2023, background): “, GPT-2, BART, OPT, and T5 [7, 12, 19]), to create NLEs describing why a given text is considered to be biased [17] or hateful [7, 17].”