Alex Mallen

15 papers A* 2Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2025 A* conf
Automatically Interpreting Millions of Features in Large Language Models.
ICML
Gonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose
2025 J jnl
Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment.
CoRR
Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks
2025 J jnl
Why Do Some Language Models Fake Alignment While Others Don't?
CoRR
Abhay Sheshadri, John Hughes, Julian Michael, Alex Mallen, Arun Jose, Janus, Fabien Roger
2024 J jnl
Automatically Interpreting Millions of Features in Large Language Models.
CoRR
Gonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose
2024 J jnl
Balancing Label Quantity and Quality for Scalable Elicitation.
CoRR
Alex Mallen, Nora Belrose
2024 A* conf
Neural Networks Learn Statistics of Increasing Complexity.
ICML
Nora Belrose, Quintin Pope, Lucia Quirke, Alex Mallen, Xiaoli Z. Fern
2024 J jnl
Neural Networks Learn Statistics of Increasing Complexity.
CoRR
Nora Belrose, Quintin Pope, Lucia Quirke, Alex Mallen, Xiaoli Z. Fern
2024 J jnl
Subversion Strategy Eval: Evaluating AI's stateless strategic capabilities against control protocols.
CoRR
Alex Mallen, Charlie Griffin, Alessandro Abate, Buck Shlegeris
2023 J jnl
Eliciting Latent Knowledge from Quirky Language Models.
CoRR
Alex Mallen, Nora Belrose
2023 J jnl
Koopman-inspired approach for identification of exogenous anomalies in nonstationary time-series data.
Mach. Learn. Sci. Technol.
Alex Mallen, Christoph A. Keller, J. Nathan Kutz
2023 J jnl
Representation Engineering: A Top-Down Approach to AI Transparency.
CoRR
Andy Zou, Long Phan, Sarah Li Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, Dan Hendrycks
2023 — conf
When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.
ACL (1)
Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, Hannaneh Hajishirzi
2022 J jnl
Koopman-theoretic Approach for Identification of Exogenous Anomalies in Nonstationary Time-series Data.
CoRR
Alex Mallen, Christoph A. Keller, J. Nathan Kutz
2022 J jnl
When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories.
CoRR
Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Hannaneh Hajishirzi, Daniel Khashabi
2021 J jnl
Deep Probabilistic Koopman: Long-term time-series forecasting under periodic uncertainties.
CoRR
Alex Mallen, Henning Lange, J. Nathan Kutz