SOTAVerified

Safety Alignment

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–288 of 288 papers

TitleStatusHype
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm—0
Adversarial Contrastive Decoding: Boosting Safety Alignment of Large Language Models via Opposite Prompt Optimization—0
Finding Safety Neurons in Large Language Models—0
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch—0
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference—0
Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual UnderstandingCode0
Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models—0
Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models—0
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner—0
On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept—0
Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens—0
One-Shot Safety Alignment for Large Language Models via Optimal DualizationCode0
Cross-Modal Safety Alignment: Is textual unlearning all you need?—0
No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks—0
Robustifying Safety-Aligned Large Language Models through Clean Data Curation—0
Safety Alignment for Vision Language Models—0
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response—0
Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching—0
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful KnowledgeCode0
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues—0
Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game—0
Enhancing Jailbreak Attacks with Diversity Guidance—0
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper—0
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement—0
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications—0
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context AttackCode0
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking—0
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models—0
How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their VulnerabilitiesCode0
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming—0
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B—0
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks—0
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations—0
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models—0
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models—0
Deceptive Alignment Monitoring—0
Model Card and Evaluations for Claude Models—0
Off-Policy Risk Assessment in Markov Decision Processes—0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.