Poster · Sydney
When Does Fine-Tuning Extract Stored Knowledge? A Relation-Covering Theory for One-Layer Transformers
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Ruichen Xu, Kexin Chen
- Organisations
- The Chinese University of Hong Kong, The Chinese University of Hong Kong, Shenzhen
- QRS classification
- Attention and transformers, Language models