AI Chat AI Image Generator AI Video Text to Speech

Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech

02/11/2023

∙

by Fan Huang, et al.

∙

∙

Recent studies have alarmed that many online hate speeches are implicit. With its subtle nature, the explainability of the detection of such hateful speech has been a challenging problem. In this work, we examine whether ChatGPT can be used for providing natural language explanations (NLEs) for implicit hateful speech detection. We design our prompt to elicit concise ChatGPT-generated NLEs and conduct user studies to evaluate their qualities by comparison with human-generated NLEs. We discuss the potential and limitations of ChatGPT in the context of implicit hateful speech research.

Fan Huang
9 publications
Haewoon Kwak
23 publications
Jisun An
23 publications

page 1

page 2

page 3

page 4

research

∙ 09/11/2022

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

Recent studies have exploited advanced generative language models to gen...

0 Fan Huang, et al. ∙

research

∙ 05/30/2023

Explaining Hate Speech Classification with Model Agnostic Methods

There have been remarkable breakthroughs in Machine Learning and Artific...

0 Durgesh Nandini, et al. ∙

research

∙ 12/28/2022

Leveraging World Knowledge in Implicit Hate Speech Detection

While much attention has been paid to identifying explicit hate speech, ...

0 Jessica Lin, et al. ∙

research

∙ 03/01/2023

ToxVis: Enabling Interpretability of Implicit vs. Explicit Toxicity Detection Models with Interactive Visualization

The rise of hate speech on online platforms has led to an urgent need fo...

0 Uma Gunturi, et al. ∙

research

∙ 01/19/2023

Warning: Humans Cannot Reliably Detect Speech Deepfakes

Speech deepfakes are artificial voices generated by machine learning mod...

0 Kimberly T. Mai, et al. ∙

research

∙ 05/28/2023

Evaluating GPT-3 Generated Explanations for Hateful Content Moderation

Recent research has focused on using large language models (LLMs) to gen...

0 Han Wang, et al. ∙

research

∙ 09/11/2021

Latent Hatred: A Benchmark for Understanding Implicit Hate Speech

Hate speech has grown significantly on social media, causing serious con...

6 Mai ElSherief, et al. ∙