Poster · Sydney
Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
- When
- Thu 10 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 6
- Authors
- Satchel Grant, Victor Gillioz, Jake Ward, Tom McGrath
- Organisations
- Goodfire, EPFL
- QRS classification
- Language models