harmful content detection

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs AAAI 2026 Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation ACL 2026 BigTokDetect: A Clinically-Informed Vision–Language Modeling Framework for Detecting Pro-Bigorexia Videos on TikTok EACL 2026 DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects ACL 2026 Failures to Surface Harmful Contents in Video Large Language Models AAAI 2026 LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026 RST-Guarder: Enhancing Long-Context Robustness for Safeguards via RST Parsing and Probabilistic Inference ACL 2026 AI Tools Can Generate Misculture Visuals! Detecting Prompts Generating Misculture Visuals For Prevention ACL 2025 AraSafe: Benchmarking Safety in Arabic LLMs EMNLP 2025 BingoGuard: LLM Content Moderation Tools with Risk Levels ICLR 2025 CALM: Curiosity-Driven Auditing for Large Language Models AAAI 2025 Conspiracy Theories and Where to Find Them on TikTok ACL 2025 ContextAware: A Multi-Agent Framework for Detecting Harmful Image-Based Comments on Social Media IJCAI 2025 Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization CVPR 2025 Distraction is All You Need for Multimodal Large Language Model Jailbreaking CVPR 2025 ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content EMNLP 2025 Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning NAACL 2025 GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection EMNLP 2025 Granite Guardian: Comprehensive LLM Safeguarding NAACL 2025 Improving Large Language Model Safety with Contrastive Representation Learning EMNLP 2025 Leveraging Large Language Models in Detecting Anti-LGBTQIA+ User-generated Texts NAACL 2025 Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025 MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection ACL 2025 MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance EMNLP 2025 MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety EMNLP 2025