Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
3
Sparse updates from surgical alignment can boost reasoning quality in LLMs, even when accuracy takes a hit.
LLMs can recognize when they lack knowledge about a referent but still choose to fabricate specific details instead of opting for safer, generic responses.
Forget slow, uninterpretable KG lookups: LogosKG unlocks interactive, billion-edge knowledge graph retrieval with orders-of-magnitude speedups by compiling symbolic queries to hardware-optimized operations.
