Search papers, labs, and topics across Lattice.
University of Waterloo
2
0
4
LexRubric reveals that even state-of-the-art LLMs struggle with open-ended legal tasks, exposing critical gaps in their contextual understanding and reasoning abilities.
Legal LLMs can be taught to respect the arrow of time, outperforming state-of-the-art models by up to 30% on legal reasoning tasks simply by enforcing temporal consistency via reinforcement learning.
