Skip to content
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

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes NeurIPS 2024 How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States EMNLP 2024 INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness NeurIPS 2024 Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates NeurIPS 2024 Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic ACL 2024 Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack NeurIPS 2024 MART: Improving LLM Safety with Multi-round Automatic Red-Teaming NAACL 2024 MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024 Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024 Navigating the OverKill in Large Language Models ACL 2024 Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models NeurIPS 2024 One-Shot Safety Alignment for Large Language Models via Optimal Dualization NeurIPS 2024 On the Vulnerability of Safety Alignment in Open-Access LLMs ACL 2024 SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding ACL 2024 Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models NeurIPS 2024 SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset NeurIPS 2024 Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack ACL 2024 Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024 Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models ICML 2024 SafeWorld: Geo-Diverse Safety Alignment NeurIPS 2024 SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types NeurIPS 2024 Should We Really Edit Language Models? On the Evaluation of Edited Language Models NeurIPS 2024 Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NeurIPS 2024 The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm EMNLP 2024 TrustAgent: Towards Safe and Trustworthy LLM-based Agents EMNLP 2024