Nathaniel Li
- Representation Engineering: A Top-Down Approach to AI Transparency
2023/10/02 by Andy Zou, Zou, Andy, Long Phan +40 · 5 voices · 155 citations
Computer Science · Engineering · #cs.LG #cs.AI #cs.CL #cs.CV #cs.CY
- Humanity's Last Exam
2025/01/24 by Long Phan, Phan, Long, Alice Gatti +2240 · 9 voices · 106 citations
#cs.LG #cs.AI #cs.CL
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
2024/02/06 by Mantas Mazeika, Long Phan, Mazeika, Mantas +21 · 234 citations
Decision Sciences · Computer Science · #Complex Systems and Decision Making #Information and Cyber Security
- LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
2024/08/27 by Nathaniel Li, Li, Nathaniel, Ziwen Han +15 · 33 citations
Social Sciences · #Computation and Language (cs.CL) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Nuclear Issues and Defense
- Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
2023/04/06 by Alexander Pan, Pan, Alexander, Andy Zou +16 · 14 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI)
- Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
2025/04/21 by Jasper Götting, Götting, Jasper, Pedro Henrique Quintela Soares de Medeiros +15 · 8 citations
Agricultural and Biological Sciences · Medicine · #Animal Disease Management and Epidemiology #Computers and Society (cs.CY) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Respiratory viral infections research