Search papers, labs, and topics across Lattice.
3
0
6
3
LLMs can be efficiently aligned with human preferences using only a small, carefully selected subset of training data, without sacrificing generalization ability.
LLMs can cut code editing costs by up to 50% simply by knowing when *not* to guess.
Optimal Transport offers a surprisingly effective and theoretically grounded approach to preference learning, outperforming existing methods in aligning LLMs with human values and reasoning abilities.
