Aidan Ewart

Undergrad student, University of Bristol

Joined

September 2023

Names

Aidan Ewart (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Homepage

Career & Education History

Undergrad student

University of Bristol (bristol.ac.uk)

2022 – 2026

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh, Stewart Slocum, Lev E McKinney, Rohit Gandikota, Aidan Ewart, Domenic Rosati, Zichu Wu, Zikui Cai, Bilal Chughtai, Yarin Gal, Furong Huang, Dylan Hadfield-Menell
- Accepted by TMLR
- Readers: Everyone
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Abhay Sheshadri, Aidan Ewart, Phillip Huang Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper
- Accepted by TMLR
- Readers: Everyone
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
Phillip Huang Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
- ICML 2025 spotlightposter
- Readers: Everyone
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
Phillip Huang Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
- Submitted to ICLR 2025
- Readers: Everyone
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Abhay Sheshadri, Aidan Ewart, Phillip Huang Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper
- Submitted to ICLR 2025
- Readers: Everyone
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Aidan Ewart, Abhay Sheshadri, Phillip Huang Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper
- SoLaR Poster
- Readers: Everyone
Robust Knowledge Unlearning via Mechanistic Localizations
Phillip Huang Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
- NextGenAISafety 2024 Poster
- Readers: Everyone
Robust Unlearning via Mechanistic Localizations
Phillip Huang Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Sparse Autoencoders Find Highly Interpretable Features in Language Models
Robert Huben, Hoagy Cunningham, Logan Riggs Smith, Aidan Ewart, Lee Sharkey
- ICLR 2024 poster
- Readers: Everyone

Co-Authors

View all 28 co-authors