Mallen, Alex

1. Representation Engineering: A Top-Down Approach to AI Transparency
   2023/10/02 by Andy Zou, Long Phan, Zou, Andy +40 · 5 voices · 158 citations
   Computer Science · Engineering · #cs.LG #cs.AI #cs.CL #cs.CV #cs.CY
2. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
   2022/12/20 by Alex Mallen, Mallen, Alex, Akari Asai +9 · 191 citations
   Computer Science · Decision Sciences · #Topic Modeling #Natural Language Processing Techniques #Data Quality and Management
3. Why Do Some Language Models Fake Alignment While Others Don't?
   2025/06/22 by Abhay Sheshadri, John Hughes, Sheshadri, Abhay +10 · 4 voices · 7 citations
   #cs.LG
4. Automatically Interpreting Millions of Features in Large Language Models
   2024/10/17 by Gonçalo Paulo, Alex Mallen, Paulo, Gonçalo +6 · 1 voice · 32 citations
   Computer Science · #Natural Language Processing Techniques #Topic Modeling
5. Neural Networks Learn Statistics of Increasing Complexity
   2024/02/06 by Belrose, Nora, Pope, Quintin, Quirke, Lucia +2 · 7 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
6. Eliciting Latent Knowledge from Quirky Language Models
   2023/12/02 by Alex Mallen, Mallen, Alex, Brumley, Madeline +2 · 5 citations
   Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
7. Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?
   2024/12/17 by Alex Mallen, Mallen, Alex, Charlie Griffin +6 · 5 citations
   Computer Science · Social Sciences · #AI-based Problem Solving and Planning #Ethics and Social Impacts of AI #Adversarial Robustness in Machine Learning
8. Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
   2025/10/06 by Nevan Wichers, Aram Ebtekar, Wichers, Nevan +19 · 4 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Software Engineering Research #Topic Modeling
9. Balancing Label Quantity and Quality for Scalable Elicitation
   2024/10/17 by Alex Mallen, Mallen, Alex, Nora Belrose +1 · 1 citation
   Pharmacology, Toxicology and Pharmaceutics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Pharmacy and Medical Practices