# Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph

arXiv: https://arxiv.org/abs/2412.15268 · HTML: https://mlsanity.com/paper/2412.15268/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 17 Dec 2024.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [One-step and Two-step Classification for Abusive Language Detection on Twitter](https://mlsanity.com/paper/1706.01206/) (2017)
- [Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis](https://mlsanity.com/paper/2308.16705/) (2023)
- [HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning](https://mlsanity.com/paper/2311.00321/) (2023)
- [Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection](https://mlsanity.com/paper/2402.11406/) (2024)
- [Towards Building a Robust Toxicity Predictor](https://mlsanity.com/paper/2404.08690/) (2024)
- [UIT-ISE-NLP at SemEval-2021 Task 5: Toxic Spans Detection with BiLSTM-CRF and ToxicBERT Comment Classification](https://mlsanity.com/paper/2104.10100/) (2021)

## Built on by (most cited first, 5 of 5)

- [Argument-Based Consistency in Toxicity Explanations of LLMs](https://mlsanity.com/paper/2506.19113/) (2025)
- [Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon](https://mlsanity.com/paper/2505.22184/) (2025)
- [Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations](https://mlsanity.com/paper/2510.20223/) (2025)
- [Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities](https://mlsanity.com/paper/2605.24000/) (2026)
- [CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension](https://mlsanity.com/paper/2608.23172/) (2026)

## Abstract (arXiv)

The rapid growth of social media platforms has raised significant concerns regarding online content toxicity. When Large Language Models (LLMs) are used for toxicity detection, two key challenges emerge: 1) the absence of domain-specific toxic knowledge leads to false negatives; 2) the excessive sensitivity of LLMs to toxic speech results in false positives, limiting freedom of speech. To address these issues, we propose a novel method called MetaTox, leveraging graph search on a meta-toxic knowledge graph to enhance hatred and toxicity detection. First, we construct a comprehensive meta-toxic knowledge graph by utilizing LLMs to extract toxic information through a three-step pipeline, with toxic benchmark datasets serving as corpora. Second, we query the graph via retrieval and ranking processes to supplement accurate, relevant toxic knowledge. Extensive experiments and in-depth case studies across multiple datasets demonstrate that our MetaTox significantly decreases the false positive rate while boosting overall toxicity detection performance. Our code is available at https://github.com/YiboZhao624/MetaTox.