# Leveraging Large Language Models and Topic Modeling for Toxicity Classification

arXiv: https://arxiv.org/abs/2411.17876 · HTML: https://mlsanity.com/paper/2411.17876/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (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)
- [Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models](https://mlsanity.com/paper/2312.08303/) (2023)
- [Exploring ChatGPT for Toxicity Detection in GitHub](https://mlsanity.com/paper/2312.13105/) (2023)
- [A Concise Review of Transfer Learning](https://mlsanity.com/paper/2104.02144/) (2021)
- [Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2410.13097/) (2024)
- [Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning](https://mlsanity.com/paper/2211.11468/) (2022)
- [Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model](https://mlsanity.com/paper/2109.10033/) (2021)
- [COVID-19-related Nepali Tweets Classification in a Low Resource Setting](https://mlsanity.com/paper/2210.05425/) (2022)

## Built on by (most cited first, 2 of 2)

- [Decentralized Low-Rank Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2501.15361/) (2025)
- [pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models](https://mlsanity.com/paper/2507.05394/) (2025)

## Abstract (arXiv)

Content moderation and toxicity classification represent critical tasks with significant social implications. However, studies have shown that major classification models exhibit tendencies to magnify or reduce biases and potentially overlook or disadvantage certain marginalized groups within their classification processes. Researchers suggest that the positionality of annotators influences the gold standard labels in which the models learned from propagate annotators' bias. To further investigate the impact of annotator positionality, we delve into fine-tuning BERTweet and HateBERT on the dataset while using topic-modeling strategies for content moderation. The results indicate that fine-tuning the models on specific topics results in a notable improvement in the F1 score of the models when compared to the predictions generated by other prominent classification models such as GPT-4, PerspectiveAPI, and RewireAPI. These findings further reveal that the state-of-the-art large language models exhibit significant limitations in accurately detecting and interpreting text toxicity contrasted with earlier methodologies. Code is available at https://github.com/aheldis/Toxicity-Classification.git.