Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
LLMs can parse complex clinical and security logs using just 1% to 2% of the original context length without sacrificing predictive performance or explanation faithfulness.
DANCE shrinks prediction sets by learning a task-specific kernel directly from the data's embeddings, offering a more efficient and robust approach to conformal prediction than relying solely on logit scores.
