Fei Mi
13 papers · 561 citations
Most-cited papers
- Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization2023 · 199 citations
- Followbench: A Multi-level Fine-grained Constraints Following Benchmark For Large Language Models2023 · 87 citations
- Unims-rag: A Unified Multi-source Retrieval-augmented Generation For Personalized Dialogue Systems2024 · 58 citations
- Cosafe: Evaluating Large Language Model Safety In Multi-turn Dialogue Coreference2024 · 50 citations
- Gaining Wisdom From Setbacks: Aligning Large Language Models Via Mistake Analysis2023 · 47 citations
Topics