mlsanityData to 7 Oct 2026

Hate Personified: Investigating the role of LLMs in content moderation

arXiv 2410.02657 ↗First posted 3 Oct 2024cs.CL cs.CYcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 24 of its 58 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

24 of 58 references.

References · 24

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  4. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  5. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  6. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 849
  7. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  8. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 403
  9. 2018Large Scale Crowdsourcing and Characterization of Twitter Abusive Behaviorcited by 265
  10. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 258
  11. 2023ChatGPT: Jack of all trades, master of nonecited by 204
  12. 2023AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotatorscited by 171
12 more
  1. 2023Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speechcited by 165
  2. 2021MultiVerS: Improving scientific claim verification with weak supervision and full-document contextcited by 140
  3. 2019Multilingual and Multi-Aspect Hate Speech Analysiscited by 133
  4. 2017Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisiscited by 95
  5. 2023Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queriescited by 82
  6. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  7. 2023Probing LLMs for hate speech detection: strengths and vulnerabilitiescited by 52
  8. 2023The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographicscited by 45
  9. 2018A Unified Deep Learning Architecture for Abuse Detectioncited by 37
  10. 2023HARE: Explainable Hate Speech Detection with Step-by-Step Reasoningcited by 30
  11. 2023Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensivecited by 16
  12. 2023Revisiting Hate Speech Benchmarks: From Data Curation to System Deploymentcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 10.

23 papers.

Sort:

By area:

  1. 2025Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Studycited by 7
  2. 2025Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regressioncited by 6
  3. 2025LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderationcited by 5
  4. 2024SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memescited by 4
  5. 2026Cultural Value Alignment Via Latent Activation Steering in Large Language Modelscited by 3
  6. 2025Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processingcited by 2
  7. 2025Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detectioncited by 2
  8. 2026Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Versioncited by 2
  9. 2024Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classificationcited by 1
  10. 2025Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Modelscited by 1
  11. 2025Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedbackcited by 1
  12. 2025Extreme Speech Classification in the Era of LLMs: Exploring Open-Source and Proprietary Modelscited by 0
11 more
  1. 2025Selective Demonstration Retrieval for Improved Implicit Hate Speech Detectioncited by 0
  2. 2025Labels or Input? Rethinking Augmentation in Multimodal Hate Detectioncited by 0
  3. 2025SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Modelscited by 0
  4. 2026How Do We Engage with Other Disciplines? A Framework to Study Meaningful Interdisciplinary Discourse in Scholarly Publicationscited by 0
  5. 2026Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLPcited by 0
  6. 2026CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMscited by 0
  7. 2026Do We Still Need Humans in the Loop? Human vs. LLM Annotation in Active Learning for TikTok Hate Speech Detectioncited by 0
  8. 2026Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Frameworkcited by 0
  9. 2026Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maximscited by 0
  10. 2026Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communitiescited by 0
  11. 2026The Safeguard Worked. Is the LLM System Safer?cited by 0