US 12,450,168 B2
Dynamic updating of content addressable associative memories for large language models
Georgios Kollias, White Plains, NY (US); Elliot Nelson, Malvern, PA (US); Payel Das, Yorktown Heights, NY (US); Subhajit Chaudhury, White Plains, NY (US); Aurelie Chloe Lozano, Scarsdale, NY (US); and Pin-Yu Chen, White Plains, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jan. 31, 2024, as Appl. No. 18/428,422.
Prior Publication US 2025/0245170 A1, Jul. 31, 2025
Int. Cl. G06F 12/12 (2016.01); G06F 12/14 (2006.01)
CPC G06F 12/12 (2013.01) [G06F 12/1466 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computerized system comprising:
a generative large language model (LLM) including an encoder configured to provide a vector input to a content addressable memory system and a decoder configured to receive a vector output from the content addressable memory system and generate a data output; and
the content addressable memory system being configured to receive the vector input and generate a vector output based on data contents of the content addressable memory system, and the content addressable memory system being configured to respond to receiving at least one memory update command by updating the data contents of the content addressable memory system.