Overview

Content moderation aims to identify material such as hate speech, harassment, self-harm, and unsafe images or videos, then guide decisions about removal, review, or rewriting. Approaches range from text classifiers and multimodal vision-language models to policy-guided language models using retrieval, examples, or step-by-step reasoning; some systems also screen content as it is generated or streamed. Researchers evaluate these methods on labeled datasets and policy-specific benchmarks, including tests of multilingual content, memes, evolving rules, and adversarial changes to text or images. A central tension is that models must apply context-dependent policies consistently while avoiding unfair errors, resisting evasion, and meeting the cost and latency limits of real moderation workflows.

Latest papers

CardsList

91 papers9 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

  1. "If It Looks Like a User": Measuring Real-Time Moderation Effects via Social Media Simulation

    Aug 17, 2026Enrico Verdolotti, Gianluca Nogara, Luca Luceri +1Content ModerationSocial Media Analysis

  2. VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation

    Aug 16, 2026Mingyu Yuan, Shengtao Wen, Lingbing Guo +2Content ModerationLLM Safety Benchmarks

  3. ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification

    Aug 2, 2026Wajdi Zaghouani, Md. Rafiul Biswas, Kholoud Khalil Aldous +1LLM Safety BenchmarksArabic NLP

  4. Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation

    Jul 30, 2026Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji +2Multimodal RobustnessAdversarial Attacks

  5. Shieldstral

    Jul 28, 2026Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273Language Model Safety EvaluationContent Moderation

  6. EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection

    Jul 24, 2026Hao Yang, Jin Wang, Xuejie ZhangContent ModerationVLM Reasoning

  7. A Dual-Hypothesis Reasoning Framework for LLM Guardrails

    Jul 20, 2026Md Asiful Islam, Fahmida Alam, Mihai SurdeanuSupervised Fine-TuningLanguage Model Safety Evaluation

  8. PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

    Jul 7, 2026Mingyang Song, Luxin Xu, Haoyu Sun +3VLM RobustnessVLM Adaptation

  9. Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection

    Jun 25, 2026Hamid Reza Firoozfar, Mohammadsadegh Abolhasani, Reza Mousavi +1Content Moderation

  10. CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges

    Jun 18, 2026Helena Bonaldi, Genoveffa Martone, Marco GueriniContent ModerationText Generation

  11. BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems

    Jun 12, 2026Leonhard Waibl, Felix Michalak, Hadrien MariacciaLLM Safety BenchmarksLLM Guardrails

  12. Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities

    Jun 11, 2026Dipto Das, Achhiya Sultana, Ankit Singh Chauhan +5Content ModerationCultural Bias in Language Models

  13. Forgive or forget: Understanding the context of hate in audio retrieval systems

    Jun 4, 2026Arghya Pal, Sailaja Rajanala, Raphael C. -W. Phan +1Content ModerationAudio-Text Retrieval

  14. When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability

    Jun 4, 2026Suraj Babu Thimma Krishnaram, Yibo Hu, Karthikeyan SaravananMultilingual Language Model EvaluationHate Speech Detection

  15. The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction

    Jun 1, 2026Mirko Lai, Alessandra Urbinati, Simona Frenda +2Annotator DisagreementConformal Prediction

  16. FigSIM: A Dataset for Fine-grained Suicide Severity and Figurative Language in Suicide Memes

    Jun 1, 2026Liuliu Chen, Elise R. Carrotte, Brian E. Chapman +2Figurative Language UnderstandingSocial Media Analysis

  17. SentGuard: Sentence-Level Streaming Guardrails for Large Language Models

    Jun 1, 2026Jiaqi Yu, Xin Wang, Yixu Wang +4Language Model Safety EvaluationLLM Guardrails

  18. TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices

    May 29, 2026Gerrit Quaremba, Elizabeth Black, Denny Vrandečić +1AI-Generated Text DetectionLanguage Model Generation Evaluation

  19. Robust and Efficient Guardrails with Latent Reasoning

    May 27, 2026Siddharth Sai, Xiaofei Wen, Muhao ChenLLM GuardrailsContent Moderation

  20. AI Content Moderation in Therapy Conversations

    May 25, 2026Jiwon Kim, Claire Wang, Taeung Yoon +2LLM AuditingLLM Guardrails