SOTAVerified

Safety Alignment

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 288 papers

TitleStatusHype
Backtracking Improves Generation Safety—0
Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap—0
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement—0
C3AI: Crafting and Evaluating Constitutions for Constitutional AI—0
Can Large Language Models Automatically Jailbreak GPT-4V?—0
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues—0
Code-Switching Curriculum Learning for Multilingual Transfer in LLMs—0
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking—0
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements—0
Cross-Modal Safety Alignment: Is textual unlearning all you need?—0
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning—0
Deceptive Alignment Monitoring—0
Mitigating Unsafe Feedback with Learning Constraints—0
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing—0
Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?—0
Don't Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning—0
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?—0
Enhancing Jailbreak Attacks with Diversity Guidance—0
Effectively Controlling Reasoning Models through Thinking Intervention—0
Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models—0
Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens—0
Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning—0
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment—0
EnJa: Ensemble Jailbreak on Large Language Models—0
Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine—0
Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models—0
ERPO: Advancing Safety Alignment via Ex-Ante Reasoning Preference Optimization—0
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions—0
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models—0
FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning—0
FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts—0
Finding Safety Neurons in Large Language Models—0
From Evaluation to Defense: Advancing Safety in Video Large Language Models—0
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring—0
"Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs—0
Internal Activation as the Polar Star for Steering Unsafe LLM Behavior—0
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations—0
Jailbreak Attacks and Defenses Against Large Language Models: A Survey—0
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models—0
JBFuzz: Jailbreaking LLMs Efficiently and Effectively Using Fuzzing—0
JULI: Jailbreak Large Language Models by Self-Introspection—0
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning—0
Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game—0
Llama-3.1-Sherkala-8B-Chat: An Open Large Language Model for Kazakh—0
LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models—0
LLM-Safety Evaluations Lack Robustness—0
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper—0
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B—0
LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models—0
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.