harmful content detection

MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025 NLP-ADBench: NLP Anomaly Detection Benchmark EMNLP 2025 Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts ACL 2025 Rainbow-Teaming for the Polish Language: A Reproducibility Study NAACL 2025 Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025 SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals EMNLP 2025 SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025 SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer Interspeech 2025 Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection EMNLP 2025 Towards an Automated Framework to Audit Youth Safety on TikTok EMNLP 2025 A Chinese Dataset for Evaluating the Safeguards in Large Language Models ACL 2024 BAN-PL: A Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl Web Service COLING 2024 Do-Not-Answer: Evaluating Safeguards in LLMs EACL 2024 Empowering Users and Mitigating Harm: Leveraging Nudging Principles to Enhance Social Media Safety COLING 2024 MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024 Please note that I’m just an AI: Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech Identification EMNLP 2024 SELF-GUARD: Empower the LLM to Safeguard Itself NAACL 2024 SLM as Guardian: Pioneering AI Safety with Small Language Model EMNLP 2024 T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition NeurIPS 2024 Towards Comprehensive Detection of Chinese Harmful Memes NeurIPS 2024 Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NeurIPS 2024 Advances in AI for Safety, Equity, and Well-Being on Web and Social Media: Detection, Robustness, Attribution, and Mitigation AAAI 2023 A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter ACL 2023 Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey EACL 2023 Towards Detecting Harmful Agendas in News Articles ACL 2023