harmful content

Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025 MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance EMNLP 2025 NetSafe: Exploring the Topological Safety of Multi-agent System ACL 2025 Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025 Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms ACL 2025 RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios? AAAI 2025 Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025 Safety Alignment via Constrained Knowledge Unlearning ACL 2025 SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025 Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025 Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models CVPR 2025 SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal ICLR 2025 Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025 Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025 TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis ACL 2025 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights ACL 2025 Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025 WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response NAACL 2025 Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey NAACL 2024 Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming EMNLP 2024 Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024 Cross-Task Defense: Instruction-Tuning LLMs for Content Safety NAACL 2024 Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! ACL 2024 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR 2024 Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis EMNLP 2024