| BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models | Oct 17, 2024 | Red TeamingSafety Alignment | CodeCode Available | 0 | 5 |
| Don't Command, Cultivate: An Exploratory Study of System-2 Alignment | Nov 26, 2024 | Prompt EngineeringSafety Alignment | CodeCode Available | 0 | 5 |
| PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling | Feb 4, 2025 | Safety Alignment | CodeCode Available | 0 | 5 |
| Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models | Dec 15, 2024 | Safety Alignment | CodeCode Available | 0 | 5 |
| LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models | Jul 3, 2024 | Safety Alignment | —Unverified | 0 | 0 |
| LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B | Oct 31, 2023 | GPURed Teaming | —Unverified | 0 | 0 |
| Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment? | May 24, 2025 | Code GenerationMath | —Unverified | 0 | 0 |
| Backtracking for Safety | Mar 11, 2025 | Safety Alignment | —Unverified | 0 | 0 |
| LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper | Feb 24, 2024 | Adversarial AttackSafety Alignment | —Unverified | 0 | 0 |
| LLM-Safety Evaluations Lack Robustness | Mar 4, 2025 | Red TeamingResponse Generation | —Unverified | 0 | 0 |
