SOTAVerified

Safety Alignment

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 226–250 of 288 papers

TitleStatusHype
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models—0
Robustifying Safety-Aligned Large Language Models through Clean Data Curation—0
SafeArena: Evaluating the Safety of Autonomous Web Agents—0
SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?—0
SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety—0
LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks—0
SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models—0
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment—0
Safe RLHF-V: Safe Reinforcement Learning from Human Feedback in Multimodal Large Language Models—0
Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models—0
Safety Alignment Can Be Not Superficial With Explicit Safety Signals—0
Safety Alignment for Vision Language Models—0
Safety Alignment via Constrained Knowledge Unlearning—0
SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation—0
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive SamplingCode0
Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability DistributionsCode0
Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak AttackingCode0
OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image ModelsCode0
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language ModelsCode0
Overriding Safety protections of Open-source ModelsCode0
One-Shot Safety Alignment for Large Language Models via Optimal DualizationCode0
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful KnowledgeCode0
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream CamouflageCode0
AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language ModelsCode0
Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning ModelCode0
Show:102550
← PrevPage 10 of 12Next →

No leaderboard results yet.