Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework
Warsaw University of Technology(华沙技术大学)
Ewelina Gajewska, Michal Wawer, Katarzyna Budzynska, Jaroslaw A. Chudziak
备注:
The paper has been accepted to the 34th European Conference on Information Systems (ECIS 2026). The official paper version will appear in the conference proceedings
The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderation systems rely on centralised, top-down rules, often failing to accommodate the subjective nature of harm perception. This paper proposes an LLM-based multi-agent personalised inference framework that filters content based on unique sensitivity profiles of individual users. Our architecture combines domain-specific Expert Agents, a Manager Agent for orchestrating content analysis and agent selection, and a Ghost Profile Agent for simulating user perspectives, to inform moderation decisions. Evaluated against a range of non-personalised baselines, the system demonstrates up to a 32% improvement in accuracy, showing increased alignment with individual user sensitivities. Beyond technical performance, our framework provides policy-relevant insights for platform governance, providing a scalable way to reconcile moderation policies with societal and individual digital rights
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
University of California, Berkeley(加州大学伯克利分校);University of Washington(华盛顿大学);Duke University(杜克大学);Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学)
SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation
East China Normal University(华东师范大学);New York University Shanghai(上海纽约大学);University of Liverpool(利物浦大学);Singapore University of Technology and Design(新加坡科技设计大学);Eastern Institute of Technology (Ningbo)(宁波东方理工大学)
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
Institute of Computing Technology, CAS(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);University of California, Merced(加州大学默塞德分校);HKUST(香港科技大学)
HiddenGuard 提出基于隐藏状态的 Prism 路由器,在令牌级别实时检测并编辑有害内容,实现细粒度安全生成,在保持信息量的同时 F1 超过 90%。
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Virginia Tech(弗吉尼亚理工大学);Salesforce Research(Salesforce研究院);University of California Berkeley(加州大学伯克利分校);University of Chicago(芝加哥大学)
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
Yang Li Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences(中国科学院计算技术研究所、中国科学院自动化研究所、中国科学院大学);Qiang Sheng Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所、中国科学院自动化研究所);Yehan Yang Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所、中国科学院自动化研究所);Xueyao Zhang The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Juan Cao Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences(中国科学院计算技术研究所、中国科学院自动化研究所、中国科学院大学)
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
Boise State University(博伊州立大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Pittsburgh(匹兹堡大学);New York University(纽约大学);Florida International University(佛罗里达国际大学)
Gender and content bias in Large Language Models: a case study on Google Gemini 2.0 Flash Experimental
University of Perugia(佩鲁贾大学);Chapin Hall at University of Chicago(芝加哥大学查平学院);Berdyansk State Pedagogical University(别尔江斯克国立师范大学);Università di Bologna(博洛尼亚大学);University of North Texas(北得克萨斯大学);Chapin Hall(查平学院)
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
Alibaba Group(阿里巴巴集团);Zhejiang University(浙江大学);Huzhou Normal University(湖州师范学院);Zhejiang Key Laboratory of Intelligent Education Technology and Application(浙江省智能教育技术与应用重点实验室)
Abusive music and song transformation using GenAI and LLMs
Transitional Artificial Intelligence Research Group, School of Mathematics and Statistics, UNSW Sydney, Australia(过渡人工智能研究组,数学与统计学学院);Centre for Artificial Intelligence and Innovation, Pingla Institute, Sydney, Australia(人工智能与创新中心,Pingla研究所)