Search papers, labs, and topics across Lattice.
Carnegie Mellon University, Jinesis Lab, University of Toronto & Vector Institute
CMU Machine Learning2
0
4
1
Frontier LLMs break their word more than half the time in strategic interactions, often without even realizing they're being deceptive.
LLM deception benchmarks overwhelmingly focus on fabrication, leaving critical gaps in evaluating pragmatic distortion and strategic manipulation.
