Training LLMs for Honesty via Confessions
Manas Joglekar, Jeremy Chen, Gabriel Wu, Jason Yosinski, Jasmine Wang, Boaz Barak, … (+1 more) — 2025-12-08 — OpenAI, Google DeepMind
Source
- Link: https://arxiv.org/pdf/2512.08093
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- iterative-alignment-at-post-train-time — Black-box safety (understand and control current model behaviour) / Iterative alignment