| Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization | Oct 5, 2023 | AllLanguage Modeling | CodeCode Available | 1 |
| All Languages Matter: On the Multilingual Safety of Large Language Models | Oct 2, 2023 | AllSafety Alignment | CodeCode Available | 1 |
| Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench | Oct 2, 2023 | BenchmarkingSafety Alignment | CodeCode Available | 1 |
| Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment | Aug 18, 2023 | MMLURed Teaming | CodeCode Available | 1 |
| BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset | Jul 10, 2023 | Question AnsweringSafety Alignment | CodeCode Available | 1 |
| TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data | Jul 8, 2025 | ChatbotInstruction Following | —Unverified | 0 |
| Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message | Jul 7, 2025 | Image GenerationSafety Alignment | —Unverified | 0 |
| Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning | Jul 6, 2025 | Safety Alignment | —Unverified | 0 |
| Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks | Jun 23, 2025 | Mixture-of-ExpertsSafety Alignment | —Unverified | 0 |
| Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs | Jun 21, 2025 | Safety Alignment | CodeCode Available | 0 |
