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

Fan Huang, Haewoon Kwak, Jisun An
2/11/2023
cs.CLcs.HC

No confident code implementation found for this paper.

Abstract

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-written NLEs. We discuss the potential and limitations of ChatGPT in the context of implicit hateful speech research.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

89% match2023

Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection

88% match2023

HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models

88% match2023

From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech

88% match1 repo2026

Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection

87% match2025

Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation

87% match2023

Cite this paper

@article{huang2023chatgpt,
  title  = {Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech},
  author = {Fan Huang and Haewoon Kwak and Jisun An},
  year   = {2023},
  eprint = {2302.07736},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.07736v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.07736.svg)](https://codeofpaper.com/paper/2302.07736)

Discussion