| ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates | Jun 17, 2024 | Instruction FollowingSafety Alignment | CodeCode Available | 1 | 5 |
| AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender | Apr 13, 2025 | Safety Alignment | CodeCode Available | 1 | 5 |
| Course-Correction: Safety Alignment Using Synthetic Preferences | Jul 23, 2024 | Safety Alignment | CodeCode Available | 1 | 5 |
| AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation | Oct 11, 2024 | Safety Alignment | CodeCode Available | 1 | 5 |
| Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique | Aug 20, 2024 | AI and SafetyDiversity | CodeCode Available | 1 | 5 |
| Can Editing LLMs Inject Harm? | Jul 29, 2024 | FairnessGeneral Knowledge | CodeCode Available | 1 | 5 |
| AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models | Oct 23, 2023 | Adversarial AttackBlocking | CodeCode Available | 1 | 5 |
| Autonomous Microscopy Experiments through Large Language Model Agents | Dec 18, 2024 | BenchmarkingExperimental Design | CodeCode Available | 1 | 5 |
| Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment | Nov 15, 2023 | Red TeamingSafety Alignment | CodeCode Available | 1 | 5 |
| Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models | Jun 9, 2025 | Multi-agent Reinforcement LearningSafety Alignment | CodeCode Available | 1 | 5 |
