Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
A three-tier evaluation framework for unsupervised narrative label generation is introduced: recovery (against a corpus's own taxonomy), mining (against external label sets), and discovery (without predefined labels).
LLMs in geopolitical simulations start out mimicking human decision-making, but quickly diverge into distinct, overly cooperative strategies that lack adversarial reasoning.
