# Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets

arXiv: https://arxiv.org/abs/2410.07991 · HTML: https://mlsanity.com/paper/2410.07991/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets](https://mlsanity.com/paper/1908.07898/) (2019)
- [On Releasing Annotator-Level Labels and Information in Datasets](https://mlsanity.com/paper/2110.05699/) (2021)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [Can ChatGPT Assess Human Personalities? A General Evaluation Framework](https://mlsanity.com/paper/2303.01248/) (2023)
- [Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms](https://mlsanity.com/paper/2310.05984/) (2023)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Spread of hate speech in online social media](https://mlsanity.com/paper/1812.01693/) (2018)
- [BiasAsker: Measuring the Bias in Conversational AI System](https://mlsanity.com/paper/2305.12434/) (2023)
- [Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions](https://mlsanity.com/paper/2205.00415/) (2022)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [Can Large Language Models Capture Dissenting Human Voices?](https://mlsanity.com/paper/2305.13788/) (2023)
- [Intersectional Bias in Hate Speech and Abusive Language Datasets](https://mlsanity.com/paper/2005.05921/) (2020)
- [The Origin and Value of Disagreement Among Data Labelers: A Case Study of the Individual Difference in Hate Speech Annotation](https://mlsanity.com/paper/2112.04030/) (2021)
- [How Crowd Worker Factors Influence Subjective Annotations: A Study of Tagging Misogynistic Hate Speech in Tweets](https://mlsanity.com/paper/2309.01288/) (2023)
- [Beyond Trial-and-Error: Predicting User Abandonment After a Moderation Intervention](https://mlsanity.com/paper/2404.14846/) (2024)

## Built on by (most cited first, 30 of 31)

- [Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents](https://mlsanity.com/paper/2502.13012/) (2025)
- [Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation](https://mlsanity.com/paper/2412.07338/) (2024)
- [Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement](https://mlsanity.com/paper/2502.06207/) (2025)
- [Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents](https://mlsanity.com/paper/2602.18462/) (2026)
- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness](https://mlsanity.com/paper/2411.08977/) (2024)
- [Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis](https://mlsanity.com/paper/2502.08663/) (2025)
- [What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma](https://mlsanity.com/paper/2505.12727/) (2025)
- [Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines](https://mlsanity.com/paper/2512.09483/) (2025)
- [Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition](https://mlsanity.com/paper/2508.08274/) (2025)
- [SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs](https://mlsanity.com/paper/2412.16783/) (2024)
- [Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMs](https://mlsanity.com/paper/2506.23610/) (2025)
- [Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection](https://mlsanity.com/paper/2510.19331/) (2025)
- [AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys](https://mlsanity.com/paper/2511.07871/) (2025)
- [When to Invoke: Refining LLM Fairness with Toxicity Assessment](https://mlsanity.com/paper/2601.09250/) (2026)
- [xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection](https://mlsanity.com/paper/2602.05874/) (2026)
- [Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication](https://mlsanity.com/paper/2501.06826/) (2025)
- [Attribute-Based Diagnosis of LLM Alignment with Hate Speech Annotations](https://mlsanity.com/paper/2605.27025/) (2026)
- [Rating the Raters: Rasch Measurement Theory for LLM Evaluation](https://mlsanity.com/paper/2608.27463/) (2026)
- [Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude](https://mlsanity.com/paper/2501.10484/) (2025)
- [Embracing Dialectic Intersubjectivity: Coordination of Different Perspectives in Content Analysis with LLM Persona Simulation](https://mlsanity.com/paper/2502.00903/) (2025)
- ["Not in My Backyard": LLMs Uncover Online and Offline Social Biases Against Homelessness](https://mlsanity.com/paper/2508.13187/) (2025)
- [From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse](https://mlsanity.com/paper/2509.14712/) (2025)
- [PRISM: Phase-enhanced Radial-based Image Signature Mapping framework for fingerprinting AI-generated images](https://mlsanity.com/paper/2509.15270/) (2025)
- [Quantifying Feature Importance for Online Content Moderation](https://mlsanity.com/paper/2510.19882/) (2025)
- [Are we chasing ghosts? Quantifying unattributable polarization, and attributing the rest to annotator groups](https://mlsanity.com/paper/2602.06055/) (2026)
- [Toward Generalized Cross-Lingual Hateful Language Detection with Web-Scale Data and Ensemble LLM Annotations](https://mlsanity.com/paper/2604.09625/) (2026)
- [Sociodemographic Biases in Educational Counselling by Large Language Models](https://mlsanity.com/paper/2604.25932/) (2026)
- [Semantic Gradients Interactions in SSD: A Case Study in Racial Identity and Hate Speech](https://mlsanity.com/paper/2605.27322/) (2026)
- [Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science](https://mlsanity.com/paper/2606.12426/) (2026)

## Abstract (arXiv)

The rise of online platforms exacerbated the spread of hate speech, demanding scalable and effective detection. However, the accuracy of hate speech detection systems heavily relies on human-labeled data, which is inherently susceptible to biases. While previous work has examined the issue, the interplay between the characteristics of the annotator and those of the target of the hate are still unexplored. We fill this gap by leveraging an extensive dataset with rich socio-demographic information of both annotators and targets, uncovering how human biases manifest in relation to the target's attributes. Our analysis surfaces the presence of widespread biases, which we quantitatively describe and characterize based on their intensity and prevalence, revealing marked differences. Furthermore, we compare human biases with those exhibited by persona-based LLMs. Our findings indicate that while persona-based LLMs do exhibit biases, these differ significantly from those of human annotators. Overall, our work offers new and nuanced results on human biases in hate speech annotations, as well as fresh insights into the design of AI-driven hate speech detection systems.