# Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments

arXiv: https://arxiv.org/abs/2505.18927 · HTML: https://mlsanity.com/paper/2505.18927/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [Challenges in Detoxifying Language Models](https://mlsanity.com/paper/2109.07445/) (2021)
- [GLUECoS : An Evaluation Benchmark for Code-Switched NLP](https://mlsanity.com/paper/2004.12376/) (2020)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Multilingual Offensive Language Identification with Cross-lingual Embeddings](https://mlsanity.com/paper/2010.05324/) (2020)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- [Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts](https://mlsanity.com/paper/2108.11830/) (2021)
- [A systematic review of Hate Speech automatic detection using Natural Language Processing](https://mlsanity.com/paper/2106.00742/) (2021)
- [Assessing the impact of contextual information in hate speech detection](https://mlsanity.com/paper/2210.00465/) (2022)
- [Automated Content Moderation Increases Adherence to Community Guidelines](https://mlsanity.com/paper/2210.10454/) (2022)

## Built on by (most cited first, 3 of 3)

- [Cyberbullying Detection via Aggression-Enhanced Prompting](https://mlsanity.com/paper/2508.06360/) (2025)
- [Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages](https://mlsanity.com/paper/2506.09992/) (2025)
- [Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Intervention](https://mlsanity.com/paper/2605.27584/) (2026)

## Abstract (arXiv)

As online platforms grow, comment sections increasingly host harassment that undermines user experience and well-being. This study benchmarks three leading large language models, OpenAI GPT-4.1, Google Gemini 1.5 Pro, and Anthropic Claude 3 Opus, on a corpus of 5,080 YouTube comments sampled from high-abuse threads in gaming, lifestyle, food vlog, and music channels. The dataset comprises 1,334 harmful and 3,746 non-harmful messages in English, Arabic, and Indonesian, annotated independently by two reviewers with substantial agreement (Cohen's kappa = 0.83). Using a unified prompt and deterministic settings, GPT-4.1 achieved the best overall balance with an F1 score of 0.863, precision of 0.887, and recall of 0.841. Gemini flagged the highest share of harmful posts (recall = 0.875) but its precision fell to 0.767 due to frequent false positives. Claude delivered the highest precision at 0.920 and the lowest false-positive rate of 0.022, yet its recall dropped to 0.720. Qualitative analysis showed that all three models struggle with sarcasm, coded insults, and mixed-language slang. These results underscore the need for moderation pipelines that combine complementary models, incorporate conversational context, and fine-tune for under-represented languages and implicit abuse. A de-identified version of the dataset and full prompts is publicly released to promote reproducibility and further progress in automated content moderation.