Search papers, labs, and topics across Lattice.
New York University
3
0
6
Emergent capabilities in transformer models arise stochastically, with larger models gaining critical skills earlier due to their ability to learn sparse attention patterns more effectively.
LLMs can ace physics exams, but put them in a universe with slightly different laws and their scientific reasoning skills fall apart.
Language models can leverage their own generative abilities to nearly eliminate forgetting during finetuning, challenging the need for stored exemplars.
