Yifei Wang
15 papers · 786 citations
Most-cited papers
- Jailbreak And Guard Aligned Language Models With Only Few In-context Demonstrations2023 · 458 citations
- Badagent: Inserting And Activating Backdoor Attacks In LLM Agents2024 · 104 citations
- A Theoretical Understanding Of Self-correction Through In-context Alignment2024 · 61 citations
Top co-authors
Topics