Cover Image

Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gajewska, Ewelina, Wawer, Michal, Budzynska, Katarzyna, Chudziak, Jaroslaw A.
Format:	Preprint
Published:	2026
Subjects:	Computers and Society Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Leveraging a Multi-Agent LLM-Based System to Educate Teachers in Hate Incidents Management
by: Gajewska, Ewelina, et al.
Published: (2025)

Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework
by: Gajewska, Ewelina, et al.
Published: (2026)

Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection
by: Gajewska, Ewelina, et al.
Published: (2025)

Predicting the winner of the US 2024 elections using trust analytics
by: Budzynska, Katarzyna, et al.
Published: (2024)

On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysis
by: Uberna, Maciej, et al.
Published: (2026)

ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction
by: Chudziak, Jarosław A., et al.
Published: (2025)

Integrating Traditional Technical Analysis with AI: A Multi-Agent LLM-Based Approach to Stock Market Forecasting
by: Wawer, Michał, et al.
Published: (2025)

The Lovelace Test of Intelligence: Can Humans Recognise and Esteem AI-Generated Art?
by: Gajewska, Ewelina
Published: (2025)

When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation
by: Wawer, Michał, et al.
Published: (2026)

Ethos and Pathos in Online Group Discussions: Corpora for Polarisation Issues in Social Media
by: Gajewska, Ewelina, et al.
Published: (2024)

Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring
by: Masłowski, Jakub, et al.
Published: (2026)

On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations
by: Sadowski, Albert, et al.
Published: (2025)

The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation
by: Zhou, Yuhang, et al.
Published: (2025)

TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Education
by: Zamojska, Monika, et al.
Published: (2025)

Multi-Agent Dialectical Refinement for Enhanced Argument Classification
by: Bąba, Jakub, et al.
Published: (2026)

GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant
by: Matak, Michał, et al.
Published: (2025)

LLM-based Semantic Augmentation for Harmful Content Detection
by: Meguellati, Elyas, et al.
Published: (2025)

HRIPBench: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs
by: Wang, Kaixuan, et al.
Published: (2025)

A Natural Language Agentic Approach to Study Affective Polarization
by: Malvicini, Stephanie Anneris, et al.
Published: (2026)

Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation
by: Herrmann, Nils A., et al.
Published: (2026)

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
by: Zhang, Chi, et al.
Published: (2025)

Critical Challenges in Content Moderation for People Who Use Drugs (PWUD): Insights into Online Harm Reduction Practices from Moderators
by: Wang, Kaixuan, et al.
Published: (2025)

Longitudinal Monitoring of LLM Content Moderation of Social Issues
by: Dai, Yunlang, et al.
Published: (2025)

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
by: Li, Yang, et al.
Published: (2025)

Harmful Suicide Content Detection
by: Park, Kyumin, et al.
Published: (2024)

Identity-related Speech Suppression in Generative AI Content Moderation
by: Proebsting, Grace, et al.
Published: (2024)

Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach
by: Sadowski, Albert, et al.
Published: (2025)

Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models
by: Bonagiri, Akash, et al.
Published: (2025)

Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation
by: Maurer, Maximilian, et al.
Published: (2026)

What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text
by: Kanepajs, Arturs, et al.
Published: (2025)

Conversational Agents to Facilitate Deliberation on Harmful Content in WhatsApp Groups
by: Agarwal, Dhruv, et al.
Published: (2024)

Who Decides in AI-Mediated Learning? The Agency Allocation Framework
by: Borchers, Conrad, et al.
Published: (2026)

Do Large Language Models Get Caught in Hofstadter-Mobius Loops?
by: Hryszko, Jaroslaw
Published: (2026)

AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
by: Ghosh, Shaona, et al.
Published: (2024)

LangLingual: A Personalised, Exercise-oriented English Language Learning Tool Leveraging Large Language Models
by: Gupta, Sammriddh, et al.
Published: (2025)

Careless Whisper: Speech-to-Text Hallucination Harms
by: Koenecke, Allison, et al.
Published: (2024)

Taxonomizing Representational Harms using Speech Act Theory
by: Corvi, Emily, et al.
Published: (2025)

PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
by: Li, Jing-Jing, et al.
Published: (2026)

AI Content Moderation in Therapy Conversations
by: Kim, Jiwon, et al.
Published: (2026)

A Capabilities Approach to Studying Bias and Harm in Language Technologies
by: Nigatu, Hellina Hailu, et al.
Published: (2024)