Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
Token-level saliency derived from a model's internal reasoning process can drastically improve the efficiency of chain-of-thought compression, outperforming traditional methods.
LLMs can now be surgically updated to not just remember facts, but also consistently *use* them in reasoning, thanks to a new method that maps and adapts the underlying causal circuits.
