Alexander Pan

PhD student, University of California, Berkeley

Joined

September 2020

Names

Alexander Pan (Preferred)

Emails

****@gmail.com (Confirmed)

****@caltech.edu (Confirmed)

****@berkeley.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

University of California, Berkeley (berkeley.edu)

2022 – 2026

Undergrad student

California Institute of Technology (caltech.edu)

2018 – 2022

Advisors, Relations & Conflicts

Advisor

Anima Anandkumar

Present

PhD Advisor

Jacob Steinhardt

Present

Expertise

No areas of expertise listed

Publications

LatentQA: Teaching LLMs to Decode Activations Into Natural Language
Alexander Pan, Lijie Chen, Jacob Steinhardt
- ICLR 2026 Poster
- Readers: Everyone
Teaching LLMs to Decode Activations Into Natural Language
Alexander Pan, Lijie Chen, Jacob Steinhardt
- Submitted to ICLR 2025
- Readers: Everyone
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Richard Ren, Steven Basart, Adam Khoja, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Alexander Pan, Gabriel Mukobi, Ryan Hwang Kim, Stephen Fitz, Dan Hendrycks
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, Jose Hernandez-Orallo, Lewis Hammond, Eric J Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak et al. (22 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Feedback Loops With Language Models Drive In-Context Reward Hacking
Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt
- ICML 2024 Poster
- Readers: Everyone
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Gabriel Mukobi, Nathan Helm-Burger, Rassin Lababidi, Lennart Justen, Andrew Bo Liu, Michael Chen, Isabelle Barrass, Oliver Zhang, Xiaoyuan Zhu, Rishub Tamirisa, Bhrugu Bharathi et al. (26 additional authors not shown)
- ICML 2024 Poster
- Readers: Everyone
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, José Hernández-Orallo, Lewis Hammond, Eric J. Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak et al. (18 additional authors not shown)
- CoRR 2024
- Readers: Everyone
Feedback Loops With Language Models Drive In-Context Reward Hacking
Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt
- ICML 2024
- Readers: Everyone
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Gabriel Mukobi, Nathan Helm-Burger, Rassin Lababidi, Lennart Justen, Andrew B. Liu, Michael Chen, Isabelle Barrass, Oliver Zhang, Xiaoyuan Zhu, Rishub Tamirisa, Bhrugu Bharathi et al. (26 additional authors not shown)
- ICML 2024
- Readers: Everyone
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Richard Ren, Steven Basart, Adam Khoja, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Alexander Pan, Gabriel Mukobi, Ryan H. Kim, Stephen Fitz, Dan Hendrycks
- CoRR 2024
- Readers: Everyone

View all 18 publications

Co-Authors

View all 128 co-authors