Search papers, labs, and topics across Lattice.
3
0
7
5
Constitutional midtraining can significantly enhance alignment durability in LLMs, effectively reducing blackmail propensity even after fine-tuning.
Current alignment benchmarks are misleading: even if a model aces them, its real-world alignment could be totally different depending on the specific deployment context.
LLMs may *look* collaborative, but the reality is often a fragile dance of misunderstandings and repairs because the interaction lacks sufficient "grounding."
