| Bayesian scaling laws for in-context learning | Oct 21, 2024 | In-Context LearningSafety Alignment | CodeCode Available | 1 |
| BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models | Oct 17, 2024 | Red TeamingSafety Alignment | CodeCode Available | 0 |
| A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement | Oct 17, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| SPIN: Self-Supervised Prompt INjection | Oct 17, 2024 | Safety Alignment | —Unverified | 0 |
| Locking Down the Finetuned LLMs Safety | Oct 14, 2024 | Safety Alignment | CodeCode Available | 1 |
| Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues | Oct 14, 2024 | LLM JailbreakSafety Alignment | CodeCode Available | 2 |
| Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation | Oct 13, 2024 | Safety AlignmentTAR | CodeCode Available | 1 |
| Can a large language model be a gaslighter? | Oct 11, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation | Oct 11, 2024 | Safety Alignment | CodeCode Available | 1 |
| Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models | Oct 11, 2024 | Safety Alignment | —Unverified | 0 |
