| Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models | Oct 4, 2023 | GPUSafety Alignment | —Unverified | 0 | 0 |
| Shape it Up! Restoring LLM Safety during Finetuning | May 22, 2025 | Safety Alignment | —Unverified | 0 | 0 |
| Smaller Large Language Models Can Do Moral Self-Correction | Oct 30, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 | 0 |
| SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge | May 27, 2025 | BenchmarkingMultiple-choice | —Unverified | 0 | 0 |
| SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models | Jan 1, 2025 | Safety Alignment | —Unverified | 0 | 0 |
| SPIN: Self-Supervised Prompt INjection | Oct 17, 2024 | Safety Alignment | —Unverified | 0 | 0 |
| STAR-1: Safer Alignment of Reasoning LLMs with 1K Data | Apr 2, 2025 | DiversitySafety Alignment | —Unverified | 0 | 0 |
| sudoLLM : On Multi-role Alignment of Language Models | May 20, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 | 0 |
| Superficial Safety Alignment Hypothesis | Oct 7, 2024 | AttributeBinary Classification | —Unverified | 0 | 0 |
| Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks | Oct 16, 2023 | Adversarial AttackFederated Learning | —Unverified | 0 | 0 |
