conftrace_

safety alignment

204 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (111) jailbreak attack (60) adversarial attack (33) harmful content (17) multimodal large language model (16) model safety (16) ai safety (13) vision-language model (13) adversarial learning (11) language model (10)

Papers

Trustworthy Medical Question Answering: An Evaluation-Centric Survey EMNLP 2025 Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron ICLR 2025 Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary EMNLP 2025 Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models ACL 2025 UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases IJCNLP 2025 VLSBench: Unveiling Visual Leakage in Multimodal Safety ACL 2025 When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning EMNLP 2025 Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region ACL 2025 WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response NAACL 2025 Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024 All Languages Matter: On the Multilingual Safety of LLMs ACL 2024 ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs ACL 2024 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ICML 2024 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NeurIPS 2024 Can Textual Unlearning Solve Cross-Modality Safety Alignment? EMNLP 2024 CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues EMNLP 2024 CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion ACL 2024 Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024 Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models EMNLP 2024 Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization ACL 2024 Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! ACL 2024 Fight Back Against Jailbreaking via Prompt Adversarial Tuning NeurIPS 2024 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR 2024 GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher ICLR 2024 GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation EMNLP 2024