| Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap | May 30, 2025 | Safety Alignment | —Unverified | 0 | 0 |
| Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement | Feb 23, 2024 | Safety Alignment | —Unverified | 0 | 0 |
| C3AI: Crafting and Evaluating Constitutions for Constitutional AI | Feb 21, 2025 | Safety Alignment | —Unverified | 0 | 0 |
| Can Large Language Models Automatically Jailbreak GPT-4V? | Jul 23, 2024 | Face RecognitionIn-Context Learning | —Unverified | 0 | 0 |
| CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues | Apr 4, 2024 | ChatbotInstruction Following | —Unverified | 0 | 0 |
| Code-Switching Curriculum Learning for Multilingual Transfer in LLMs | Nov 4, 2024 | Cross-Lingual TransferLanguage Acquisition | —Unverified | 0 | 0 |
| Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking | Nov 16, 2023 | Safety Alignment | —Unverified | 0 | 0 |
| Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements | Oct 11, 2024 | Safety Alignment | —Unverified | 0 | 0 |
| Cross-Modal Safety Alignment: Is textual unlearning all you need? | May 27, 2024 | AllSafety Alignment | —Unverified | 0 | 0 |
| CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning | May 22, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 | 0 |
