Poster · Sydney
Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Matteo Leonesi, Francesco Belardinelli, Flavio Corradini, Marco Piangerelli
- Organisations
- University of Camerino, Imperial College London
- QRS classification
- Language models