# Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2312.15099 · HTML: https://mlsanity.com/paper/2312.15099/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 28 of its 101 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [Supervised Multimodal Bitransformers for Classifying Images and Text](https://mlsanity.com/paper/1909.02950/) (2019)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance](https://mlsanity.com/paper/2305.17306/) (2023)
- [Fuzz4All: Universal Fuzzing with Large Language Models](https://mlsanity.com/paper/2308.04748/) (2023)
- ["HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media](https://mlsanity.com/paper/2304.10619/) (2023)
- [Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisis](https://mlsanity.com/paper/2005.12423/) (2020)
- [On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning](https://mlsanity.com/paper/2212.06573/) (2022)
- [Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech](https://mlsanity.com/paper/2209.04889/) (2022)
- [FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems](https://mlsanity.com/paper/2304.14746/) (2023)
- [Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXEL](https://mlsanity.com/paper/2004.13850/) (2020)
- [ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection](https://mlsanity.com/paper/2205.12495/) (2022)
- [LAMBRETTA: Learning to Rank for Twitter Soft Moderation](https://mlsanity.com/paper/2212.05926/) (2022)
- [Capitol (Pat)riots: A comparative study of Twitter and Parler](https://mlsanity.com/paper/2101.06914/) (2021)
- [Analyzing Right-wing YouTube Channels: Hate, Violence and Discrimination](https://mlsanity.com/paper/1804.04096/) (2018)
- [Twitter Dataset on the Russo-Ukrainian War](https://mlsanity.com/paper/2204.08530/) (2022)

## Built on by (most cited first, 18 of 18)

- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection](https://mlsanity.com/paper/2402.00371/) (2024)
- [Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models](https://mlsanity.com/paper/2403.18957/) (2024)
- [HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns](https://mlsanity.com/paper/2501.16750/) (2025)
- [MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance](https://mlsanity.com/paper/2505.14483/) (2025)
- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [Supporting Human Raters with the Detection of Harmful Content using Large Language Models](https://mlsanity.com/paper/2406.12800/) (2024)
- [LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation](https://mlsanity.com/paper/2503.07237/) (2025)
- [ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection](https://mlsanity.com/paper/2508.11281/) (2025)
- [Evaluating Large Language Models for Detecting Antisemitism](https://mlsanity.com/paper/2509.18293/) (2025)
- [Black Box Absorption: LLMs Undermining Innovative Ideas](https://mlsanity.com/paper/2510.20612/) (2025)
- [Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages](https://mlsanity.com/paper/2506.09992/) (2025)
- [Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages](https://mlsanity.com/paper/2506.23930/) (2025)
- [Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework](https://mlsanity.com/paper/2601.09342/) (2026)
- [Towards Training-free Multimodal Hate Localisation with Large Language Models](https://mlsanity.com/paper/2602.09637/) (2026)
- [CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs](https://mlsanity.com/paper/2604.10502/) (2026)
- [CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation](https://mlsanity.com/paper/2604.10504/) (2026)
- [LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation](https://mlsanity.com/paper/2609.33521/) (2026)

## Abstract (arXiv)

Online hate is an escalating problem that negatively impacts the lives of Internet users, and is also subject to rapid changes due to evolving events, resulting in new waves of online hate that pose a critical threat. Detecting and mitigating these new waves present two key challenges: it demands reasoning-based complex decision-making to determine the presence of hateful content, and the limited availability of training samples hinders updating the detection model. To address this critical issue, we present a novel framework called HATEGUARD for effectively moderating new waves of online hate. HATEGUARD employs a reasoning-based approach that leverages the recently introduced chain-of-thought (CoT) prompting technique, harnessing the capabilities of large language models (LLMs). HATEGUARD further achieves prompt-based zero-shot detection by automatically generating and updating detection prompts with new derogatory terms and targets in new wave samples to effectively address new waves of online hate. To demonstrate the effectiveness of our approach, we compile a new dataset consisting of tweets related to three recently witnessed new waves: the 2022 Russian invasion of Ukraine, the 2021 insurrection of the US Capitol, and the COVID-19 pandemic. Our studies reveal crucial longitudinal patterns in these new waves concerning the evolution of events and the pressing need for techniques to rapidly update existing moderation tools to counteract them. Comparative evaluations against state-of-the-art tools illustrate the superiority of our framework, showcasing a substantial 22.22% to 83.33% improvement in detecting the three new waves of online hate. Our work highlights the severe threat posed by the emergence of new waves of online hate and represents a paradigm shift in addressing this threat practically.