US 12,242,468 B1
Generative machine learning with retriever having reconfigurable sequence of rankers
Eliot P. Brenner, Westfield, NJ (US); Koustuv Dasgupta, Scarsdale, NY (US); Dinesh Gupta, Princeton, NJ (US); Manjunath G. Hegde, Bangalore (IN); Amy Francesca Pajak, London (GB); Goncalo Nuno Ventura de Melo, London (GB); and Abdallah Mohamed Abdo Mohamed Bashir, London (GB)
Assigned to Goldman Sachs & Co. LLC, New York, NY (US)
Filed by Goldman Sachs & Co. LLC, New York, NY (US)
Filed on Aug. 7, 2024, as Appl. No. 18/797,294.
Application 18/797,294 is a continuation of application No. 18/659,799, filed on May 9, 2024.
Claims priority of application No. 202311078197 (IN), filed on Nov. 17, 2023.
Int. Cl. G06F 16/242 (2019.01); G06F 16/2452 (2019.01); G06F 16/2457 (2019.01)
CPC G06F 16/242 (2019.01) [G06F 16/24522 (2019.01); G06F 16/24578 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining an input query at a retriever model, the retriever model comprising a reconfigurable sequence of one or more rankers selected from among a plurality of rankers, each ranker configured to identify a specified number of information chunks relevant to the input query;
providing one or more of the information chunks from the retriever model to a generative model;
using the generative model to create a response to the input query, the response based on the one or more information chunks; and
tuning the retriever model by determining the specified number of information chunks to be identified by each ranker in the reconfigurable sequence;
wherein the plurality of rankers comprises a bi-encoder, a cross-encoder, and a large language model (LLM)-ranker; and
wherein the specified number of information chunks to be identified by each ranker in the reconfigurable sequence is determined using a grid search.