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

arXiv: https://arxiv.org/abs/2310.13985 · HTML: https://mlsanity.com/paper/2310.13985/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 41 references that are in the map.
- First posted on arXiv 21 Oct 2023.

## Builds on (most cited first, 13 of 13)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks](https://mlsanity.com/paper/2304.10145/) (2023)
- [Evaluating GPT-3 Generated Explanations for Hateful Content Moderation](https://mlsanity.com/paper/2305.17680/) (2023)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022)
- [Countering hate on social media: Large scale classification of hate and counter speech](https://mlsanity.com/paper/2006.01974/) (2020)
- [Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization](https://mlsanity.com/paper/2206.04007/) (2022)
- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [Impact and dynamics of hate and counter speech online](https://mlsanity.com/paper/2009.08392/) (2020)
- [A Graph-Based Context-Aware Model to Understand Online Conversations](https://mlsanity.com/paper/2211.09207/) (2022)

## Built on by (most cited first, 8 of 8)

- [What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection](https://mlsanity.com/paper/2402.00371/) (2024)
- [CodeMirage: Hallucinations in Code Generated by Large Language Models](https://mlsanity.com/paper/2408.08333/) (2024)
- [MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models](https://mlsanity.com/paper/2409.19492/) (2024)
- [MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages](https://mlsanity.com/paper/2404.02037/) (2024)
- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [Overview of the HASOC Subtrack at FIRE 2023: Identification of Tokens Contributing to Explicit Hate in English by Span Detection](https://mlsanity.com/paper/2311.09834/) (2023)
- [Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text](https://mlsanity.com/paper/2510.03683/) (2025)
- [When Does Span-Guided Detoxification Help? Human Preferences and Evaluator Diagnostics in a Controlled Comparison](https://mlsanity.com/paper/2607.26795/) (2026)

## Abstract (arXiv)

Hate speech has become pervasive in today's digital age. Although there has been considerable research to detect hate speech or generate counter speech to combat hateful views, these approaches still cannot completely eliminate the potential harmful societal consequences of hate speech -- hate speech, even when detected, can often not be taken down or is often not taken down enough; and hate speech unfortunately spreads quickly, often much faster than any generated counter speech. This paper investigates a relatively new yet simple and effective approach of suggesting a rephrasing of potential hate speech content even before the post is made. We show that Large Language Models (LLMs) perform well on this task, outperforming state-of-the-art baselines such as BART-Detox. We develop 4 different prompts based on task description, hate definition, few-shot demonstrations and chain-of-thoughts for comprehensive experiments and conduct experiments on open-source LLMs such as LLaMA-1, LLaMA-2 chat, Vicuna as well as OpenAI's GPT-3.5. We propose various evaluation metrics to measure the efficacy of the generated text and ensure the generated text has reduced hate intensity without drastically changing the semantic meaning of the original text. We find that LLMs with a few-shot demonstrations prompt work the best in generating acceptable hate-rephrased text with semantic meaning similar to the original text. Overall, we find that GPT-3.5 outperforms the baseline and open-source models for all the different kinds of prompts. We also perform human evaluations and interestingly, find that the rephrasings generated by GPT-3.5 outperform even the human-generated ground-truth rephrasings in the dataset. We also conduct detailed ablation studies to investigate why LLMs work satisfactorily on this task and conduct a failure analysis to understand the gaps.