# Hate Personified: Investigating the role of LLMs in content moderation

arXiv: https://arxiv.org/abs/2410.02657 · HTML: https://mlsanity.com/paper/2410.02657/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators](https://mlsanity.com/paper/2303.16854/) (2023)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries](https://mlsanity.com/paper/2310.13132/) (2023)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Probing LLMs for hate speech detection: strengths and vulnerabilities](https://mlsanity.com/paper/2310.12860/) (2023)
- [The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics](https://mlsanity.com/paper/2306.11559/) (2023)
- [A Unified Deep Learning Architecture for Abuse Detection](https://mlsanity.com/paper/1802.00385/) (2018)
- [HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning](https://mlsanity.com/paper/2311.00321/) (2023)
- [Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive](https://mlsanity.com/paper/2301.12534/) (2023)
- [Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment](https://mlsanity.com/paper/2306.01105/) (2023)

## Built on by (most cited first, 25 of 25)

- [Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study](https://mlsanity.com/paper/2505.06149/) (2025)
- [Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression](https://mlsanity.com/paper/2508.08509/) (2025)
- [LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation](https://mlsanity.com/paper/2503.07237/) (2025)
- [SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes](https://mlsanity.com/paper/2412.20541/) (2024)
- [Cultural Value Alignment Via Latent Activation Steering in Large Language Models](https://mlsanity.com/paper/2605.26365/) (2026)
- [Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing](https://mlsanity.com/paper/2503.05280/) (2025)
- [Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection](https://mlsanity.com/paper/2510.19331/) (2025)
- [Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version](https://mlsanity.com/paper/2606.11399/) (2026)
- [Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classification](https://mlsanity.com/paper/2410.20490/) (2024)
- [Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models](https://mlsanity.com/paper/2506.08593/) (2025)
- [Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback](https://mlsanity.com/paper/2510.16257/) (2025)
- [Extreme Speech Classification in the Era of LLMs: Exploring Open-Source and Proprietary Models](https://mlsanity.com/paper/2502.15155/) (2025)
- [Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection](https://mlsanity.com/paper/2504.12082/) (2025)
- [Labels or Input? Rethinking Augmentation in Multimodal Hate Detection](https://mlsanity.com/paper/2508.11808/) (2025)
- [SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models](https://mlsanity.com/paper/2509.15174/) (2025)
- [How Do We Engage with Other Disciplines? A Framework to Study Meaningful Interdisciplinary Discourse in Scholarly Publications](https://mlsanity.com/paper/2601.17020/) (2026)
- [Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP](https://mlsanity.com/paper/2603.28351/) (2026)
- [CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs](https://mlsanity.com/paper/2604.10502/) (2026)
- [Do We Still Need Humans in the Loop? Human vs. LLM Annotation in Active Learning for TikTok Hate Speech Detection](https://mlsanity.com/paper/2604.13899/) (2026)
- [Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework](https://mlsanity.com/paper/2605.01416/) (2026)
- [Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims](https://mlsanity.com/paper/2606.02493/) (2026)
- [Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communities](https://mlsanity.com/paper/2607.07277/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)
- [To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation](https://mlsanity.com/paper/2610.03324/) (2026)
- [Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages](https://mlsanity.com/paper/2610.18588/) (2026)

## Abstract (arXiv)

For subjective tasks such as hate detection, where people perceive hate differently, the Large Language Model's (LLM) ability to represent diverse groups is unclear. By including additional context in prompts, we comprehensively analyze LLM's sensitivity to geographical priming, persona attributes, and numerical information to assess how well the needs of various groups are reflected. Our findings on two LLMs, five languages, and six datasets reveal that mimicking persona-based attributes leads to annotation variability. Meanwhile, incorporating geographical signals leads to better regional alignment. We also find that the LLMs are sensitive to numerical anchors, indicating the ability to leverage community-based flagging efforts and exposure to adversaries. Our work provides preliminary guidelines and highlights the nuances of applying LLMs in culturally sensitive cases.