| Align in Depth: Defending Jailbreak Attacks via Progressive Answer Detoxification | Mar 14, 2025 | Safety Alignment | —Unverified | 0 |
| Representation-based Reward Modeling for Efficient Safety Alignment of Large Language Model | Mar 13, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| JBFuzz: Jailbreaking LLMs Efficiently and Effectively Using Fuzzing | Mar 12, 2025 | Red TeamingSafety Alignment | —Unverified | 0 |
| Backtracking for Safety | Mar 11, 2025 | Safety Alignment | —Unverified | 0 |
| Utilizing Jailbreak Probability to Attack and Safeguard Multimodal LLMs | Mar 10, 2025 | Binary ClassificationSafety Alignment | —Unverified | 0 |
| SafeArena: Evaluating the Safety of Autonomous Web Agents | Mar 6, 2025 | MisinformationSafety Alignment | —Unverified | 0 |
| Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety | Mar 6, 2025 | Decision MakingSafety Alignment | —Unverified | 0 |
| SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning | Mar 5, 2025 | Safe Reinforcement LearningSafety Alignment | —Unverified | 0 |
| LLM-Safety Evaluations Lack Robustness | Mar 4, 2025 | Red TeamingResponse Generation | —Unverified | 0 |
| Llama-3.1-Sherkala-8B-Chat: An Open Large Language Model for Kazakh | Mar 3, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
