conftrace_

safety alignment

178 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) adversarial attack (1621) model safety (101) harmful content (66) multimodal large language model (966) ai safety (235) language model (4599) llm safety (67) adversarial learning (1595)

Papers

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion ACL 2024
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024
Can Textual Unlearning Solve Cross-Modality Safety Alignment? EMNLP 2024
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States EMNLP 2024
Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024
GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation EMNLP 2024
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024
MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding ACL 2024
All Languages Matter: On the Multilingual Safety of LLMs ACL 2024
UNIWIZ: A Unified Large Language Model Orchestrated Wizard for Safe Knowledge Grounded Conversations ACL 2024
Vulnerabilities of Large Language Models to Adversarial Attacks ACL 2024
Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! ACL 2024
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming NAACL 2024
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness NIPS 2024
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm EMNLP 2024
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024
TrustAgent: Towards Safe and Trustworthy LLM-based Agents EMNLP 2024
On the Vulnerability of Safety Alignment in Open-Access LLMs ACL 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
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack ACL 2024
Navigating the OverKill in Large Language Models ACL 2024
One-Shot Safety Alignment for Large Language Models via Optimal Dualization NIPS 2024
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset NIPS 2024